Claude Opus 4.6
- Input price
- $5.00
- Per 1 million tokens (USD)
- Output price
- $25.00
- Per 1 million tokens (USD)
- Effort levels
- 4total
- Default: High
- Benchmark results
- 11total
- Benchmark types: 11
Model information
- API model ID
- claude-opus-4-6
- release date
- Unknown
- effort
- Low / Med / High (default) / Max
- Effort source
- Based on Anthropic effort documentation (platform.claude.com/docs/en/build-with-claude/effort).
- Claude Code
- available
- Codex
- unavailable
- Availability notes
- 1M context with `claude-opus-4-6[1m]` (including Max/Ultra/Team/Enterprise). Codex's official model list (learn.chatgpt.com/docs/models) contains only OpenAI models, so codex is false (connections via a custom provider are not counted as official options).
- Availability source
- https://code.claude.com/docs/en/model-config
Price (USD per 1 million tokens)
Prices do not vary by effort; token consumption does.
| input | $5.00 |
|---|---|
| output | $25.00 |
| cache read | $0.50 |
| cache write | $6.25 |
cacheWritePerMTok is for a 5-minute cache write. 1h write $10.
Claude Opus 4.6 | $5 / MTok | $6.25 / MTok | $10 / MTok | $0.50 / MTok | $25 / MTokSource: https://platform.claude.com/docs/en/about-claude/pricing
Benchmark results
| Benchmark | effort | Score | Source cost (metric) | measured/reported by | source | Conditions and extraction method |
|---|---|---|---|---|---|---|
| Humanity's Last Exam (with tools)Max | Max | 53.0% | — | Anthropic | Introducing Claude Opus 4.6official · Retrieved 2026-11-13 | Vendor-reported value (announced by Anthropic). Text values in the main text and the footnote (the table and figure were not used because they are images). Tools: web search, web fetch, code execution, programmatic tool calling; context compression at 50k (maximum 3M); max reasoning effort; adaptive thinking. Updated from 53.1% following improved cheating detection.transcribed from textSource excerpt[Feb 23, 2026] Updated reported score for Opus 4.6 for HLE with tools (53.1% to 53.0%).Location Update note at the end of Footnotes on the Opus 4.6 announcement page. The effort is in the Humanity’s Last Exam entry in the same Footnotes (max reasoning effort) |
| CyberGymnot stated | not stated | 73.8% | — | Anthropic | Introducing Claude Opus 4.7official · Retrieved 2026-11-13 | Vendor-reported value (announced by Anthropic). Text values in the main text and the footnote (the table and figure were not used because they are images). Value after updating harness parameters. Effort not stated.transcribed from textSource excerptCyberGym: Opus 4.6’s score has been updated from the originally reported 66.6 to 73.8, as we updated our harness parameters to better elicit cyber capability.Location Opus 4.7 announcement page, CyberGym entry in Footnotes |
| GPQA DiamondMax | Max | 88.4% | — | 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 "Claude Opus 4.6 (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=claude-opus-4-6_max, Best score (across scorers)=0.8838383838383839, stderr=0.02282888177524936, Started at=2026-08-06T23:57:58.000ZLocation gpqa_diamond.csv, data row 121 (file line 179), id=JcQMgXdZKU54u52B8TGQKp, Model version=claude-opus-4-6_max |
| FrontierMath Tiers 1-3(v2)Max | Max | 66.0% | — | 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 "Claude Opus 4.6 (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=claude-opus-4-6_max, Best score (across scorers)=0.6596491228070176, stderr=0.028116467881852295, Started at=2026-06-11T00:19:44.000ZLocation frontiermath_tiers_1_3_v2.csv, data row 119 (file line 149), id=kgJ2d6XbKj3dZutDcBYSKU, Model version=claude-opus-4-6_max |
| FrontierMath Tier 4(v2)Max | Max | 26.8% | — | 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 "Claude Opus 4.6 (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=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 |
| OTIS Mock AIME 2024-2025Max | Max | 91.1% | — | 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 "Claude Opus 4.6 (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=claude-opus-4-6_max, Best score (across scorers)=0.9111111111111111, stderr=0.04290254662948546, Started at=2026-08-06T23:58:17.000ZLocation otis_mock_aime_2024_2025.csv, data row 132 (file line 197), id=coxYk5vK5cBhQ7iZohMtA5, Model version=claude-opus-4-6_max |
| SimpleQA VerifiedMax | Max | 47.0% | — | 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 "Claude Opus 4.6 (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=claude-opus-4-6_max, Best score (across scorers)=0.47, stderr=0.015790799515836722, Started at=2026-08-27T19:27:45.000ZLocation simpleqa_verified.csv, data row 87 (file line 137), id=85fhMxLaebWtLoi6oLpTbi, Model version=claude-opus-4-6_max |
| Chess Puzzles(Epoch AI)Max | Max | 21.0% | — | 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 "Claude Opus 4.6 (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=claude-opus-4-6_max, Best score (across scorers)=0.21, stderr=0.040936018074033236, Started at=2026-10-13T13:43:19.000ZLocation chess_puzzles.csv, data row 98 (file line 149), id=aKc2rzsA6YPYwCkE7nhvvB, Model version=claude-opus-4-6_max |
| MirrorCodeMax | Max | 33.3% | — | 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 "Claude Opus 4.6 (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=claude-opus-4-6_max, Best score (across scorers)=0.3333333333333333, stderr=0.10026420125303973, Started at=2026-10-21T16:48:25.000ZLocation mirrorcode.csv, data row 19 (file line 24), id=Q8sNp4aYrjtYQgVS3BRDTd, Model version=claude-opus-4-6_max |
| Epoch Capabilities Index(ECI)not stated | not stated | 156.34 | — | 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=Claude Opus 4.6, eci=156.34, eci_ci_low=154.55, eci_ci_high=158.31Location epoch_capabilities_index/eci_scores.csv, data row 37 (file line 38), Model=Claude Opus 4.6 |
| τ²-bench banking_knowledge (v1.0.1)Max | Max | 27.3% | — | Sierra | τ²-bench leaderboard submission claude-opus-4-6_sierra_2026-05-05 (sierra-research/tau2-bench, MIT)third-party · Retrieved 2026-11-13 | τ²-bench leaderboard submission claude-opus-4-6_sierra_2026-05-05 (submission_type standard, tau2_bench_version 1.0.1). Submitter "Sierra", model_organization "Anthropic": Run by Sierra, which operates τ²-bench (third-party measurement). Verified by the leaderboard (prompts not modified, no questions omitted). Trajectories are not public (preliminary comparison). The value is pass^1 (%). reasoning_effort "max". User simulator gpt-5.2 (reasoning_effort low). Search configuration retrieval_config "alltools". Evaluation date 2026-05-06. Notes summary: rescored on 2026-07-15 following a scoring correction in v1.0.1; 4 trial runs; seed 300.transcribed from tableSource excerptbanking_knowledge.pass_1=27.32Location In submissions/claude-opus-4-6_sierra_2026-05-05/submission.json: results.banking_knowledge.pass_1 (line 22 of file). model_name "Claude Opus 4.6". verification.details (line 39) is "Trajectories suppressed for this preliminary AllTools comparison". methodology.notes (line 35) |
Related rankings
- Overall ranking (all models, records)
- Humanity's Last Exam (with tools) ranking by metric (all models, records)
- CyberGym 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)
- τ²-bench banking_knowledge (v1.0.1) ranking by metric (all models, records)
- Recommendations by role