GPT-6 Sol
- Input price
- $2.00
- Per 1 million tokens (USD)
- Output price
- $10.00
- Per 1 million tokens (USD)
- Effort levels
- 6total
- Default: Med
- Benchmark results
- 20total
- Benchmark types: 12
Model information
- API model ID
- gpt-6-sol
- release date
- 2026-09-22
- effort
- None / Low / Med (default) / High / Xhigh / Max
- Effort source
- Based on reasoning effort on the OpenAI model page (developers.openai.com/api/docs/models/gpt-6-sol).
- Claude Code
- unavailable
- Codex
- unknown
- Availability notes
- Model page: 'See GPT-6.1 Sol for the newer Sol model.' (no deprecation announcement). Not stated on the Codex models page. Claude Code's official model list (code.claude.com/docs/en/model-config alias table) contains only Anthropic models, so claudeCode is false (connections via a gateway are not counted as official options).
- Availability source
- https://developers.openai.com/api/docs/models/gpt-6-sol
Price (USD per 1 million tokens)
Prices do not vary by effort; token consumption does.
| input | $2.00 |
|---|---|
| output | $10.00 |
| cache read | $0.20 |
| cache write | $2.50 |
Prompts with more than 272K input tokens are priced at 2x input and cache rates and 1.5x output for the full request. Batch/Flex 50%, Fast 2x.
| gpt-6-sol | $2.00 | $10.00 | $0.20 | $2.50 | $5.00 | $4.00 | $15.00 | $0.40 | $5.00 | $10.00 |Benchmark results
| Benchmark | effort | Score | Source cost (metric) | measured/reported by | source | Conditions and extraction method |
|---|---|---|---|---|---|---|
| FrontierCode v1.1(main set)Low | Low | 37.3% | $0.43Cost per task | not stated | Introducing Claude Sonnet 5.5official · Retrieved 2026-11-12 | Vendor-reported value. A point in the figure "FrontierCode v1.1, main set / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for a model from some other vendor (announced by Anthropic); the figure's effort label "Low" was mapped to low in the OpenAI API reasoning efforttranscribed from textSource excerptFrontierCode v1.1, main set — Accuracy vs. cost: "GPT-6 Sol · Low: 37.3% $0.43" |
| FrontierCode v1.1(main set)Med (default) | Med | 45.9% | $0.77Cost per task | not stated | Introducing Claude Sonnet 5.5official · Retrieved 2026-11-12 | Vendor-reported value. A point in the figure "FrontierCode v1.1, main set / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for a model from some other vendor (announced by Anthropic); the figure's effort label "Med" was mapped to medium in the OpenAI API reasoning efforttranscribed from textSource excerptFrontierCode v1.1, main set — Accuracy vs. cost: "GPT-6 Sol · Med: 45.9% $0.77" |
| FrontierCode v1.1(main set)High | High | 47.7% | $1.04Cost per task | not stated | Introducing Claude Sonnet 5.5official · Retrieved 2026-11-12 | Vendor-reported value. A point in the figure "FrontierCode v1.1, main set / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for a model from some other vendor (announced by Anthropic); the figure's effort label "High" was mapped to high in the OpenAI API reasoning efforttranscribed from textSource excerptFrontierCode v1.1, main set — Accuracy vs. cost: "GPT-6 Sol · High: 47.7% $1.04" |
| FrontierCode v1.1(main set)Xhigh | Xhigh | 48.4% | $1.32Cost per task | not stated | Introducing Claude Sonnet 5.5official · Retrieved 2026-11-12 | Vendor-reported value. A point in the figure "FrontierCode v1.1, main set / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for a model from some other vendor (announced by Anthropic); the figure's effort label "Xhigh" was mapped to xhigh in the OpenAI API reasoning efforttranscribed from textSource excerptFrontierCode v1.1, main set — Accuracy vs. cost: "GPT-6 Sol · Xhigh: 48.4% $1.32" |
| FrontierCode v1.1(main set)Max | Max | 49.3% | $2.07Cost per task | not stated | Introducing Claude Sonnet 5.5official · Retrieved 2026-11-12 | Vendor-reported value. A point in the figure "FrontierCode v1.1, main set / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for a model from some other vendor (announced by Anthropic); the figure's effort label "Max" was mapped to max in the OpenAI API reasoning efforttranscribed from textSource excerptFrontierCode v1.1, main set — Accuracy vs. cost: "GPT-6 Sol · Max: 49.3% $2.07" |
| GDPval-AA v2.1not stated | not stated | 1,487 | — | Artificial Analysis | Introducing Claude Sonnet 5.5official · Retrieved 2026-11-12 | Vendor-reported value. table note: For details on how we run our evaluations, see the Sonnet 5.5 System Card (only efforts explicitly stated in the table); footnote 3: run by Artificial Analysis on a pre-release deployment (structured outputs bug, now fixed); footnote 4: the GPT-6 Sol image understanding bug fix may not be reflected in the official score; values for other vendor models (as listed by Anthropic)transcribed from tableSource excerpt1487Location Table, GDPval-AA v2.1 row: 1487 |
| AA-Briefcase v1.1(Elo)Low | Low | 905 | $0.12Cost per task | not stated | Introducing Claude Sonnet 5.5official · Retrieved 2026-11-12 | Vendor-reported value. A point in the figure "AA-Briefcase v1.1 / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for a model from some other vendor (announced by Anthropic); the figure's effort label "Low" was mapped to low in the OpenAI API reasoning efforttranscribed from textSource excerptAA-Briefcase v1.1 — Accuracy vs. cost: "GPT-6 Sol · Low: 905.0 $0.12" |
| AA-Briefcase v1.1(Elo)Med (default) | Med | 1,142 | $0.34Cost per task | not stated | Introducing Claude Sonnet 5.5official · Retrieved 2026-11-12 | Vendor-reported value. A point in the figure "AA-Briefcase v1.1 / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for a model from some other vendor (announced by Anthropic); the figure's effort label "Med" was mapped to medium in the OpenAI API reasoning efforttranscribed from textSource excerptAA-Briefcase v1.1 — Accuracy vs. cost: "GPT-6 Sol · Med: 1142.0 $0.34" |
| AA-Briefcase v1.1(Elo)High | High | 1,289 | $0.63Cost per task | not stated | Introducing Claude Sonnet 5.5official · Retrieved 2026-11-12 | Vendor-reported value. A point in the figure "AA-Briefcase v1.1 / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for a model from some other vendor (announced by Anthropic); the figure's effort label "High" was mapped to high in the OpenAI API reasoning efforttranscribed from textSource excerptAA-Briefcase v1.1 — Accuracy vs. cost: "GPT-6 Sol · High: 1289.0 $0.63" |
| AA-Briefcase v1.1(Elo)Xhigh | Xhigh | 1,364 | $1.19Cost per task | not stated | Introducing Claude Sonnet 5.5official · Retrieved 2026-11-12 | Vendor-reported value. A point in the figure "AA-Briefcase v1.1 / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for a model from some other vendor (announced by Anthropic); the figure's effort label "Xhigh" was mapped to xhigh in the OpenAI API reasoning efforttranscribed from textSource excerptAA-Briefcase v1.1 — Accuracy vs. cost: "GPT-6 Sol · Xhigh: 1364.0 $1.19" |
| AA-Briefcase v1.1(Elo)Max | Max | 1,483 | $2.67Cost per task | not stated | Introducing Claude Sonnet 5.5official · Retrieved 2026-11-12 | Vendor-reported value. A point in the figure "AA-Briefcase v1.1 / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for a model from some other vendor (announced by Anthropic); the figure's effort label "Max" was mapped to max in the OpenAI API reasoning efforttranscribed from textSource excerptAA-Briefcase v1.1 — Accuracy vs. cost: "GPT-6 Sol · Max: 1483.0 $2.67" |
| Chartography (without tools)not stated | not stated | 53.6% | — | not stated | Introducing Claude Sonnet 5.5official · Retrieved 2026-11-12 | Vendor-reported value. table note: For details on how we run our evaluations, see the Sonnet 5.5 System Card (only efforts explicitly stated in the table); footnote 4: the GPT-6 Sol image understanding bug fix may not be reflected in the official score; values for other vendor models (as listed by Anthropic)transcribed from tableSource excerpt53.6%Location Table, Chartography (no tools) row: 53.6 |
| GPQA DiamondMax | Max | 94.3% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0third-party · Retrieved 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.transcribed from tableSource excerptgpqa_diamond.csv: Model version=gpt-6-sol_max, Best score (across scorers)=0.9431818181818182, stderr=0.014938512008159717, Started at=2026-09-22T19:59:24.000ZLocation gpqa_diamond.csv, data row 22 (file line 46), id=aJD7ZfFftu2cZoToJhhzF7, Model version=gpt-6-sol_max |
| FrontierMath Tiers 1-3(v2)Max | Max | 89.8% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tiers_1_3_v2.csv) CC BY 4.0third-party · Retrieved 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.transcribed from tableSource excerptfrontiermath_tiers_1_3_v2.csv: Model version=gpt-6-sol_max, Best score (across scorers)=0.8982456140350877, stderr=0.01793969072128637, Started at=2026-09-22T19:59:24.000ZLocation frontiermath_tiers_1_3_v2.csv, data row 16 (file line 29), id=RHjHEPHEsWZqFuMjBTeC6r, Model version=gpt-6-sol_max |
| FrontierMath Tier 4(v2)Max | Max | 90.0% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0third-party · Retrieved 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.transcribed from tableSource 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 |
| OTIS Mock AIME 2024-2025Max | Max | 100.0% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, otis_mock_aime_2024_2025.csv) CC BY 4.0third-party · Retrieved 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.transcribed from tableSource excerptotis_mock_aime_2024_2025.csv: Model version=gpt-6-sol_max, Best score (across scorers)=1.0, stderr=0.0, Started at=2026-09-22T19:59:24.000ZLocation otis_mock_aime_2024_2025.csv, data row 24 (file line 48), id=VZAUcNkzeMSMm9paxBhj6B, Model version=gpt-6-sol_max |
| SimpleQA VerifiedMax | Max | 60.7% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, simpleqa_verified.csv) CC BY 4.0third-party · Retrieved 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.transcribed from tableSource excerptsimpleqa_verified.csv: Model version=gpt-6-sol_max, Best score (across scorers)=0.607, stderr=0.015452824654081525, Started at=2026-09-22T19:59:24.000ZLocation simpleqa_verified.csv, data row 22 (file line 46), id=donMeEKBZZdqpQsojKWJEm, Model version=gpt-6-sol_max |
| Chess Puzzles(Epoch AI)Max | Max | 56.0% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, chess_puzzles.csv) CC BY 4.0third-party · Retrieved 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.transcribed from tableSource excerptchess_puzzles.csv: Model version=gpt-6-sol_max, Best score (across scorers)=0.56, stderr=0.049888765156985884, Started at=2026-10-13T13:41:42.000ZLocation chess_puzzles.csv, data row 105 (file line 159), id=N9uFn7EZFsvHNcHEwEy3J6, Model version=gpt-6-sol_max |
| MirrorCodeMax | Max | 48.9% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, mirrorcode.csv) CC BY 4.0third-party · Retrieved 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.transcribed from tableSource excerptmirrorcode.csv: Model version=gpt-6-sol_max, Best score (across scorers)=0.4888888888888889, stderr=0.11205944504585896, Started at=2026-10-29T18:04:31.000ZLocation mirrorcode.csv, data row 4 (file line 5), id=TQ4LXFJtzphWHf9brvHq5i, Model version=gpt-6-sol_max |
| Epoch Capabilities Index(ECI)not stated | not stated | 163.75 | — | Epoch AI | Epoch AI, epoch_capabilities_index/eci_scores.csv (CC BY 4.0)third-party · Retrieved 2026-11-12 | A per-model metric that combines results across multiple benchmarks and multiple efforts (not per effort). Calculated by Epoch AI.transcribed from tableSource excerpteci_scores.csv: Model=GPT-6 Sol, eci=163.75, eci_ci_low=161.33, eci_ci_high=166.42Location epoch_capabilities_index/eci_scores.csv, data row 12 (file line 13), Model=GPT-6 Sol |
Related rankings
- Overall ranking (all models, records)
- FrontierCode v1.1(main set) ranking by metric (all models, records)
- GDPval-AA v2.1 ranking by metric (all models, records)
- AA-Briefcase v1.1(Elo) ranking by metric (all models, records)
- Chartography (without tools) ranking by metric (all models, records)
- GPQA Diamond ranking by metric (all models, records)
- FrontierMath Tiers 1-3(v2) ranking by metric (all models, records)
- FrontierMath Tier 4(v2) ranking by metric (all models, records)
- OTIS Mock AIME 2024-2025 ranking by metric (all models, records)
- SimpleQA Verified ranking by metric (all models, records)
- Chess Puzzles(Epoch AI) ranking by metric (all models, records)
- MirrorCode ranking by metric (all models, records)
- Epoch Capabilities Index(ECI) ranking by metric (all models, records)
- Recommendations by role