FrontierMath Tier 4(v2)
FrontierMath's most difficult Tier 4 (v2, private).
- Category
- Math
- Unit
- Percent (%)
- Higher is better
- Comparison groups
- 1total
- Currently available model rankings · Ranked results: 13
- All models (records): Groups: 1 · Entries: 42
Rankings
Values with different source types (official, third-party, paper) or measurement conditions cannot be compared, so rankings are separated by comparison group (the same source, or sources verified to use the same conditions).
Rankings include only models currently available in Claude Code / Codex, excluding legacy models.
- View on rankings page (by metric)
- Cost balance (frontier and effort changes)
- Overall ranking (performance first)
third-party results (Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0)
| Rank | Model | effort | Score | Source cost (metric) | measured/reported by | source |
|---|---|---|---|---|---|---|
| 1 | Claude Fable 5.2 | Max | 100.0% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Fable 5.2 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=claude-fable-5-2_max, Best score (across scorers)=1.0, stderr=0.0, Started at=2026-11-06T01:14:45.000Z |
| 1 | GPT-6.1 Sol | Max | 100.0% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6.1 Sol (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gpt-6.1-sol_max, Best score (across scorers)=1.0, stderr=0.0, Started at=2026-09-29T22:00:34.000Z |
| 3 | GPT-6 Astra | High | 97.6% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6 Astra (high)". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gpt-6-astra_high, Best score (across scorers)=0.976, stderr=0.024, Started at=2026-08-30T02:22:12.000Z |
| 3 | GPT-6 Astra | Xhigh | 97.6% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6 Astra (xhigh)". effort is indicated by the suffix _xhigh in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gpt-6-astra_xhigh, Best score (across scorers)=0.976, stderr=0.024, Started at=2026-08-30T02:22:12.000Z |
| 3 | GPT-6 Astra | Max | 97.6% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6 Astra (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gpt-6-astra_max, Best score (across scorers)=0.976, stderr=0.024, Started at=2026-08-30T02:22:12.000Z |
| 6 | GPT-6 Astra | Med | 97.6% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6 Astra (medium)". effort is indicated by the suffix _medium in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gpt-6-astra_medium, Best score (across scorers)=0.975609756097561, stderr=0.024390243902439022, Started at=2026-08-30T02:22:12.000Z |
| 7 | Claude Opus 5.5 | Max | 95.0% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Opus 5.5 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=claude-opus-5-5_max, Best score (across scorers)=0.95, stderr=0.041175470771058854, Started at=2026-09-22T18:27:39.000Z |
| 8 | GPT-6.1 Terra | Max | 92.7% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6.1 Terra (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gpt-6.1-terra_max, Best score (across scorers)=0.926829268292683, stderr=0.04117547077105886, Started at=2026-10-26T20:00:37.000Z |
| 9 | GPT-6 Astra | Low | 87.8% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6 Astra (low)". effort is indicated by the suffix _low in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gpt-6-astra_low, Best score (across scorers)=0.8780487804878049, stderr=0.051739520574625435, Started at=2026-08-30T02:22:12.000Z |
| 10 | GPT-6 Astra | not stated | 82.9% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6 Astra (none)". effort is indicated by the suffix _none in Epoch's Model version. Data retrieved 2026-11-12. No effort because the source effort label "none" is not in the official effort list.Source excerptfrontiermath_tier_4_v2.csv: Model version=gpt-6-astra_none, Best score (across scorers)=0.8292682926829268, stderr=0.05949419959829497, Started at=2026-08-30T02:22:12.000Z |
| 11 | Claude Sonnet 5.5 | Max | 80.5% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Sonnet 5.5 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=claude-sonnet-5-5_max, Best score (across scorers)=0.8048780487804879, stderr=0.06265967111543964, Started at=2026-09-29T15:15:14.000Z |
| 12 | GPT-6 Luna | Max | 56.1% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6 Luna (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gpt-6-luna_max, Best score (across scorers)=0.5609756097560976, stderr=0.07846686801046543, Started at=2026-09-22T22:14:05.000Z |
| 13 | Claude Haiku 5.5 | Max | 46.3% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Haiku 5.5 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=claude-haiku-5-5_max, Best score (across scorers)=0.4634146341463415, stderr=0.07884502378168105, Started at=2026-10-07T20:42:31.000Z |
All model rankings (records)
These rankings are recalculated by comparison group including legacy models and models unavailable in Claude Code / Codex. They differ from the rankings above because the set of models differs.
- View all model rankings (by metric)
- Cost balance (all models, records)
- Overall ranking (all models, records)
Show rankings including legacy and unavailable models (entries: 42)
third-party results (Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0)
| Rank | Model | effort | Score | Source cost (metric) | measured/reported by | source |
|---|---|---|---|---|---|---|
| 1 | Claude Fable 5.2 | Max | 100.0% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Fable 5.2 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=claude-fable-5-2_max, Best score (across scorers)=1.0, stderr=0.0, Started at=2026-11-06T01:14:45.000Z |
| 1 | GPT-6.1 Sol | Max | 100.0% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6.1 Sol (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gpt-6.1-sol_max, Best score (across scorers)=1.0, stderr=0.0, Started at=2026-09-29T22:00:34.000Z |
| 3 | GPT-6 Astra | High | 97.6% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6 Astra (high)". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gpt-6-astra_high, Best score (across scorers)=0.976, stderr=0.024, Started at=2026-08-30T02:22:12.000Z |
| 3 | GPT-6 Astra | Xhigh | 97.6% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6 Astra (xhigh)". effort is indicated by the suffix _xhigh in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gpt-6-astra_xhigh, Best score (across scorers)=0.976, stderr=0.024, Started at=2026-08-30T02:22:12.000Z |
| 3 | GPT-6 Astra | Max | 97.6% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6 Astra (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gpt-6-astra_max, Best score (across scorers)=0.976, stderr=0.024, Started at=2026-08-30T02:22:12.000Z |
| 6 | GPT-6 Astra | Med | 97.6% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6 Astra (medium)". effort is indicated by the suffix _medium in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gpt-6-astra_medium, Best score (across scorers)=0.975609756097561, stderr=0.024390243902439022, Started at=2026-08-30T02:22:12.000Z |
| 7 | Gemini 4 Carbon | High | 95.1% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Gemini 4 Carbon (high)". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gemini-4-carbon_high, Best score (across scorers)=0.9512195121951219, stderr=0.03405912205797303, Started at=2026-11-02T23:17:42.000Z |
| 8 | Claude Opus 5.5 | Max | 95.0% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Opus 5.5 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=claude-opus-5-5_max, Best score (across scorers)=0.95, stderr=0.041175470771058854, Started at=2026-09-22T18:27:39.000Z |
| 9 | GPT-6.1 Terra | Max | 92.7% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6.1 Terra (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gpt-6.1-terra_max, Best score (across scorers)=0.926829268292683, stderr=0.04117547077105886, Started at=2026-10-26T20:00:37.000Z |
| 10 | Claude Fable 5 | Max | 90.2% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Fable 5 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=claude-fable-5_max, Best score (across scorers)=0.902, stderr=0.046, Started at=2026-06-09T18:12:35.000ZLocation frontiermath_tier_4_v2.csv, data row 81 (file line 120), id=ReDAtJGGfRtrEGGWf4Zbsd, Model version=claude-fable-5_max |
| 11 | GPT-6 Sol | Max | 90.0% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6 Sol (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gpt-6-sol_max, Best score (across scorers)=0.9, stderr=0.051739520574625435, Started at=2026-09-22T19:59:24.000ZLocation frontiermath_tier_4_v2.csv, data row 16 (file line 29), id=jwS3LYLCPbZpHDzzkX6LyV, Model version=gpt-6-sol_max |
| 12 | GPT-6 Astra | Low | 87.8% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6 Astra (low)". effort is indicated by the suffix _low in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gpt-6-astra_low, Best score (across scorers)=0.8780487804878049, stderr=0.051739520574625435, Started at=2026-08-30T02:22:12.000Z |
| 13 | GPT-6 Astra | not stated | 82.9% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6 Astra (none)". effort is indicated by the suffix _none in Epoch's Model version. Data retrieved 2026-11-12. No effort because the source effort label "none" is not in the official effort list.Source excerptfrontiermath_tier_4_v2.csv: Model version=gpt-6-astra_none, Best score (across scorers)=0.8292682926829268, stderr=0.05949419959829497, Started at=2026-08-30T02:22:12.000Z |
| 13 | GPT-5.6 Sol | Max | 82.9% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-5.6 Sol (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gpt-5.6-sol_max, Best score (across scorers)=0.8292682926829268, stderr=0.05949419959829497, Started at=2026-07-09T02:45:09.000ZLocation frontiermath_tier_4_v2.csv, data row 47 (file line 84), id=QJ5rJMVypB4PMxPcBGftc8, Model version=gpt-5.6-sol_max |
| 15 | Claude Sonnet 5.5 | Max | 80.5% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Sonnet 5.5 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=claude-sonnet-5-5_max, Best score (across scorers)=0.8048780487804879, stderr=0.06265967111543964, Started at=2026-09-29T15:15:14.000Z |
| 16 | Gemini 4 Argon | High | 78.1% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Gemini 4 Argon (high)". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gemini-4-argon_high, Best score (across scorers)=0.7804878048780488, stderr=0.06544589202438408, Started at=2026-10-13T17:14:57.000Z |
| 17 | GPT-5.5 | Xhigh | 72.5% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-5.5 (xhigh)". effort is indicated by the suffix _xhigh in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gpt-5.5_xhigh, Best score (across scorers)=0.725, stderr=0.07149950690165274, Started at=2026-06-11T17:47:36.000ZLocation frontiermath_tier_4_v2.csv, data row 70 (file line 107), id=PKSMspJiJdNThB6qNvaBSM, Model version=gpt-5.5_xhigh |
| 18 | GPT-5.6 Terra | Max | 70.7% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-5.6 Terra (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gpt-5.6-terra_max, Best score (across scorers)=0.7073170731707317, stderr=0.07194088392074452, Started at=2026-07-09T15:58:30.000ZLocation frontiermath_tier_4_v2.csv, data row 45 (file line 82), id=ZUygpkXqg3NjchXXfedAWV, Model version=gpt-5.6-terra_max |
| 19 | Kimi K3.1 Pro | Max | 65.9% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Kimi K3.1 Pro (Together, max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12. Epoch ran it via Together's inference API (Model version kimi-k3.1-pro-together).Source excerptfrontiermath_tier_4_v2.csv: Model version=kimi-k3.1-pro-together_max, Best score (across scorers)=0.6585365853658537, stderr=0.07497768853141171, Started at=2026-11-06T00:59:23.000ZLocation frontiermath_tier_4_v2.csv, data row 2 (file line 3), id=o7TxEhAxnN2qKUqqhFgp5H, Model version=kimi-k3.1-pro-together_max |
| 20 | GPT-5.6 Luna | Max | 61.0% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-5.6 Luna (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gpt-5.6-luna_max, Best score (across scorers)=0.6097560975609756, stderr=0.07712872341874097, Started at=2026-07-09T14:18:35.000ZLocation frontiermath_tier_4_v2.csv, data row 46 (file line 83), id=NLiiJJSyA9wmg2FHENFpAq, Model version=gpt-5.6-luna_max |
| 21 | GPT-6 Luna | Max | 56.1% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6 Luna (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gpt-6-luna_max, Best score (across scorers)=0.5609756097560976, stderr=0.07846686801046543, Started at=2026-09-22T22:14:05.000Z |
| 21 | Claude Opus 4.8 | Max | 56.1% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Opus 4.8". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=claude-opus-4-8_max, Best score (across scorers)=0.5609756097560976, stderr=0.07846686801046543, Started at=2026-06-10T15:25:15.000ZLocation frontiermath_tier_4_v2.csv, data row 80 (file line 119), id=JiqgqBTfkGx797uowZgJbk, Model version=claude-opus-4-8_max |
| 23 | Claude Haiku 5.5 | Max | 46.3% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Haiku 5.5 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=claude-haiku-5-5_max, Best score (across scorers)=0.4634146341463415, stderr=0.07884502378168105, Started at=2026-10-07T20:42:31.000Z |
| 23 | Qwen3.8-Max | Xhigh | 46.3% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Qwen3.8 Max (xhigh)". effort is indicated by the suffix _xhigh in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=qwen3.8-max_xhigh, Best score (across scorers)=0.4634146341463415, stderr=0.07884502378168105, Started at=2026-08-04T19:32:51.000ZLocation frontiermath_tier_4_v2.csv, data row 36 (file line 69), id=PBRdMZyz4L4CqPpXyLD2Lk, Model version=qwen3.8-max_xhigh |
| 23 | DeepSeek-V4.1-Flash-1017 | Max | 46.3% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "DeepSeek V4.1 Flash 1017 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=deepseek-v4.1-flash-1017_max, Best score (across scorers)=0.4634146341463415, stderr=0.07884502378168105, Started at=2026-10-19T22:39:00.000ZLocation frontiermath_tier_4_v2.csv, data row 5 (file line 6), id=jnCfi6VttQBv3t54B3xp9G, Model version=deepseek-v4.1-flash-1017_max |
| 26 | Kimi K3 | Max | 39.0% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Kimi K3 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=kimi-k3_max, Best score (across scorers)=0.3902439024390244, stderr=0.07712872341874095, Started at=2026-07-17T01:48:42.000ZLocation frontiermath_tier_4_v2.csv, data row 42 (file lines 77-79; multi-line record), id=gZERSAQwxBAevQzBsWfUie, Model version=kimi-k3_max |
| 27 | Gemini 3.7 Flash | High | 36.6% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Gemini 3.7 Flash (high)". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gemini-3.7-flash_high, Best score (across scorers)=0.36585365853658536, stderr=0.07615851217559022, Started at=2026-08-14T19:59:58.000ZLocation frontiermath_tier_4_v2.csv, data row 32 (file line 65), id=KptKXK5nE2Ns2WbiaSSnbc, Model version=gemini-3.7-flash_high |
| 28 | Grok 4.6 | Xhigh | 31.7% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Grok 4.6 (xhigh)". effort is indicated by the suffix _xhigh in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=grok-4.6_xhigh, Best score (across scorers)=0.3170731707317073, stderr=0.07357611282438223, Started at=2026-08-14T15:46:50.000ZLocation frontiermath_tier_4_v2.csv, data row 34 (file line 67), id=bg3JRdd33iWfvRoGSvyXXE, Model version=grok-4.6_xhigh |
| 28 | Claude Opus 4.7 | Max | 31.7% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Opus 4.7 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=claude-opus-4-7_max, Best score (across scorers)=0.3170731707317073, stderr=0.07357611282438223, Started at=2026-06-10T21:41:54.000ZLocation frontiermath_tier_4_v2.csv, data row 77 (file line 116), id=P4LXQ9PyDDziEANMB5jVRd, Model version=claude-opus-4-7_max |
| 30 | GLM-5.3 | Max | 29.3% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GLM-5.3 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=glm-5.3_max, Best score (across scorers)=0.2926829268292683, stderr=0.07194088392074452, Started at=2026-08-25T14:20:20.000ZLocation frontiermath_tier_4_v2.csv, data row 30 (file line 63), id=4S3ZrJDkwh4gmGrmJQdvzR, Model version=glm-5.3_max |
| 31 | Mistral Large 4 | High | 26.8% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Mistral Large 4 Preview (high)". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12. Epoch's label is Mistral Large 4 Preview (2026-10-06 version; Mistral Large 4 from 2026-10-29 has a different Model version, mistral-large-4-0-oss, and is not included here).Source excerptfrontiermath_tier_4_v2.csv: Model version=mistral-large-4-0_high, Best score (across scorers)=0.2682926829268293, stderr=0.07005564203095158, Started at=2026-10-12T21:38:35.000ZLocation frontiermath_tier_4_v2.csv, data row 8 (file lines 9-20; multi-line record), id=TzoNRjKto6wEuZ5PmQPAw8, Model version=mistral-large-4-0_high |
| 31 | Gemini 3.1 Pro Preview | not stated | 26.8% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Gemini 3.1 Pro Preview". No effort suffix in Model version. Data retrieved 2026-11-12. No effort because effort is not stated in the source.Source excerptfrontiermath_tier_4_v2.csv: Model version=gemini-3.1-pro-preview, Best score (across scorers)=0.2682926829268293, stderr=0.07005564203095158, Started at=2026-06-11T23:35:57.000ZLocation frontiermath_tier_4_v2.csv, data row 66 (file line 103), id=eXVWr3RBeSsWy5DAU8ed46, Model version=gemini-3.1-pro-preview |
| 31 | Claude Opus 4.6 | Max | 26.8% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Opus 4.6 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=claude-opus-4-6_max, Best score (across scorers)=0.2682926829268293, stderr=0.07005564203095158, Started at=2026-06-11T00:19:44.000ZLocation frontiermath_tier_4_v2.csv, data row 76 (file line 115), id=2hbbp8z6PhB7c2T33os9q5, Model version=claude-opus-4-6_max |
| 31 | DeepSeek-V4-Pro-0813 | Max | 26.8% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "DeepSeek V4 Pro 0813 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=deepseek-v4-pro-0813_max, Best score (across scorers)=0.2682926829268293, stderr=0.07005564203095158, Started at=2026-08-19T13:35:48.000ZLocation frontiermath_tier_4_v2.csv, data row 31 (file line 64), id=a4uV8HMMBAcHXLVSmZfBgX, Model version=deepseek-v4-pro-0813_max |
| 31 | DeepSeek-V4.1-Flash | not stated | 26.8% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "DeepSeek V4.1 Flash (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12. No effort for the source effort label "max" because the official effort list has not been collected.Source excerptfrontiermath_tier_4_v2.csv: Model version=deepseek-v4.1-flash_max, Best score (across scorers)=0.2682926829268293, stderr=0.07005564203095158, Started at=2026-10-08T19:02:32.000ZLocation frontiermath_tier_4_v2.csv, data row 10 (file lines 22-23; multi-line record), id=KansJcyeGR4m7G4p8GupDn, Model version=deepseek-v4.1-flash_max |
| 36 | Gemini 3.8 Flash | High | 22.0% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Gemini 3.8 Flash (high)". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gemini-3.8-flash_high, Best score (across scorers)=0.21951219512195122, stderr=0.06544589202438408, Started at=2026-09-02T17:15:36.000ZLocation frontiermath_tier_4_v2.csv, data row 21 (file line 34), id=Lgy52ZT4YpFrUqqKVu2qUs, Model version=gemini-3.8-flash_high |
| 36 | Gemini 3.6 Flash | High | 22.0% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Gemini 3.6 Flash". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gemini-3.6-flash_high, Best score (across scorers)=0.21951219512195122, stderr=0.06544589202438408, Started at=2026-08-02T00:36:45.000ZLocation frontiermath_tier_4_v2.csv, data row 40 (file line 75), id=JCMjXU6FRiiLV3xvs9R2Xv, Model version=gemini-3.6-flash_high |
| 38 | Grok 4.7 | Xhigh | 17.1% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Grok 4.7 (xhigh)". effort is indicated by the suffix _xhigh in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=grok-4.7_xhigh, Best score (across scorers)=0.17073170731707318, stderr=0.05949419959829495, Started at=2026-09-22T21:49:22.000ZLocation frontiermath_tier_4_v2.csv, data row 15 (file line 28), id=Ymgj5VeEceBbzsLq6xEZRi, Model version=grok-4.7_xhigh |
| 38 | Gemini 3 Flash Preview | not stated | 17.1% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Gemini 3 Flash Preview". No effort suffix in Model version. Data retrieved 2026-11-12. No effort because effort is not stated in the source.Source excerptfrontiermath_tier_4_v2.csv: Model version=gemini-3-flash-preview, Best score (across scorers)=0.17073170731707318, stderr=0.05949419959829497, Started at=2026-06-11T23:44:30.000ZLocation frontiermath_tier_4_v2.csv, data row 65 (file line 102), id=ZczEhu69FQ9Cnns8NT6ew4, Model version=gemini-3-flash-preview |
| 38 | GLM-5.3-Flash | Max | 17.1% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GLM-5.3-Flash (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=glm-5.3-flash_max, Best score (across scorers)=0.17073170731707318, stderr=0.05949419959829495, Started at=2026-08-27T13:29:52.000ZLocation frontiermath_tier_4_v2.csv, data row 29 (file lines 60-62; multi-line record), id=iCysWvFJevNyw2dbYosU6J, Model version=glm-5.3-flash_max |
| 41 | Gemini 3.5 Flash-Lite | High | 0.0% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Gemini 3.5 Flash-Lite". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.Source excerptfrontiermath_tier_4_v2.csv: Model version=gemini-3.5-flash-lite_high, Best score (across scorers)=0.0, stderr=0.0, Started at=2026-08-02T01:20:17.000ZLocation frontiermath_tier_4_v2.csv, data row 39 (file line 74), id=juNVfKBcYTwaKnk9GRA2zL, Model version=gemini-3.5-flash-lite_high |
| 41 | Gemini 2.5 Pro | not stated | 0.0% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "gemini-2.5-pro". No effort suffix in Model version. Data retrieved 2026-11-12. No effort because effort is not stated in the source.Source excerptfrontiermath_tier_4_v2.csv: Model version=gemini-2.5-pro, Best score (across scorers)=0.0, stderr=0.0, Started at=2026-06-11T23:56:12.000ZLocation frontiermath_tier_4_v2.csv, data row 64 (file line 101), id=2z7kL9DpfvY44T9Wo99FYx, Model version=gemini-2.5-pro |