claude-opus-4-1-20250805: benchmark scores, price and ranking
claude-opus-4-1-20250805 from Anthropic ranks #239 of 743 LLMs on the LLMs Tiger aggregate benchmark score (49.7), based on 11 benchmark results captured up to 2026-10-13.
- Organisation
- Anthropic
- Type
- Frontier model
- Open weights
- No
- Released
- 2025-08-05 (source: name)
- Aggregate rank
- #239 of 743 (score 49.7)
Relative to other models, claude-opus-4-1-20250805 is strongest on Cybench (#2 of 16) and weakest on EBR-Bench (#20 of 21).
Across the 10 benchmarks where at least ten models are scored, claude-opus-4-1-20250805 is in the top 10% on 0 and in the top half on 6.
claude-opus-4-1-20250805 benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| Cybench | 42.0% | #2 of 16 | Epoch AI Benchmarking Hub | 2026-10-13 |
| DeepResearch Bench | 48.3% | #1 of 7 | Epoch AI Benchmarking Hub | 2026-10-13 |
| SimpleBench | 60.0% | #9 of 61 | Epoch AI Benchmarking Hub | 2026-10-13 |
| SWE-bench Verified | 73.3% | #13 of 73 | Epoch AI Benchmarking Hub | 2026-10-13 |
| METR time horizon | 100 min | #8 of 31 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Terminal-Bench 2.0 | 38.0% | #13 of 28 | Epoch AI Benchmarking Hub | 2026-10-13 |
| GPQA Diamond | 73.2% | #134 of 275 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Chess Puzzles | 7.0% | #71 of 122 | Epoch AI Benchmarking Hub | 2026-10-13 |
| WebDev Arena | 1,386 | #40 of 67 | Epoch AI Benchmarking Hub | 2026-10-13 |
| OTIS Mock AIME | 40.0% | #113 of 189 | Epoch AI Benchmarking Hub | 2026-10-13 |
| EBR-Bench | 7.9% | #20 of 21 | Epoch AI Benchmarking Hub | 2026-10-13 |
About claude-opus-4-1-20250805
claude-opus-4-1-20250805 is a frontier model from Anthropic. It was released on 2025-08-05, according to the model's own name. No API price is listed for it yet. We hold 11 benchmark results for it across 4 areas, and none is in the top tenth of its board.
Where claude-opus-4-1-20250805 stands
On our aggregate score, claude-opus-4-1-20250805 is #239 of 743 ranked models, around the middle of the table. Its score is 49.7; the scale is centred on 50, so it sits 0.3 points below the typical model. That beats 68% of the ranked field. Among the 70 ranked Anthropic models it is #42. The next one up is claude-haiku-4-5-20251001_1K at 49.8. The next one down is claude-sonnet-4-20250514_16K at 49.7.
claude-opus-4-1-20250805, benchmark by benchmark
Cybench puts claude-opus-4-1-20250805 at 42.0%, #2 of 16. That beats 88% of the models tested, but 1.0 points short of grok-4-0709 (43.0%). The results either side are grok-4-0709 (43.0%) and grok-4-1 (39.0%). It covers cybersecurity capture-the-flag tasks. The board median is 17.5%, so claude-opus-4-1-20250805 is 24.5 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
On SimpleBench, claude-opus-4-1-20250805 reaches 60.0%. It ranks #9 of 61, ahead of 85% of the field, and 21.9 points behind Claude Fable 5 (max) at 81.9%. The results either side are Claude Opus 4.1 (unknown thinking) (60.0%) and Claude Opus 4 (58.8%). It covers trick questions that test common sense. The board median is 41.4%, so claude-opus-4-1-20250805 is 18.6 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
claude-opus-4-1-20250805 manages 73.3% on SWE-bench Verified, good for #13 of 73. Claude Opus 4.7 (max) leads at 83.5%, 10.1 points further up, and 82% of models sit below. The results either side are GPT-5 (high) (73.6%) and GLM-5 (72.8%). It covers real GitHub issues resolved. The board median is 56.4%, so claude-opus-4-1-20250805 is 16.9 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
METR time horizon puts claude-opus-4-1-20250805 at 100 min, #8 of 31. That beats 74% of the models tested, but 944 minutes short of Claude Mythos Preview (Early) (1,045 min). The results either side are grok-4-0709 (110 min) and Claude Opus 4 (100 min). It covers length of task (minutes) done at 50% success. The board median is 23 min, so claude-opus-4-1-20250805 is 77 minutes above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
On Terminal-Bench 2.0, claude-opus-4-1-20250805 reaches 38.0%. It ranks #13 of 28, ahead of 54% of the field, and 31.4 points behind Gemini 3 Pro Preview at 69.4%. The results either side are DeepSeek-V3.2 (Thinking; Novita) (39.6%) and Claude Opus 4.1 (unknown thinking) (38.0%). It covers real terminal tasks (agent + model). The board median is 37.3%, so claude-opus-4-1-20250805 is 0.7 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
claude-opus-4-1-20250805 manages 73.2% on GPQA Diamond, good for #134 of 275. GPT-6 Astra (max) leads at 95.8%, 22.5 points further up, and 51% of models sit below. The results either side are A.X-K1 (74.0%) and Gemma 4 26B A4B (73.2%). It covers expert-level science questions. The board median is 71.7%, so claude-opus-4-1-20250805 is 1.5 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
claude-opus-4-1-20250805 lands below the middle on Chess Puzzles: 7.0%, #71 of 122, with 57% of the field scoring higher. GPT-6 Astra (max) leads at 72.0%; the closest result above is Claude Opus 4.7 (max) at 7.0%. It covers chess tactics puzzles. The board median is 12.5%, so claude-opus-4-1-20250805 is 5.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
claude-opus-4-1-20250805 lands below the middle on WebDev Arena: 1,386, #40 of 67, with 58% of the field scoring higher. Claude Opus 5.5 (max) leads at 1,820; the closest result above is MiniMax-M2.1 at 1,387. It covers building web apps, crowd-voted (Elo). The board median is 1,433, so claude-opus-4-1-20250805 is 47 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
claude-opus-4-1-20250805 lands below the middle on OTIS Mock AIME: 40.0%, #113 of 189, with 59% of the field scoring higher. Claude Fable 5.1 (max) leads at 100.0%; the closest result above is deepseek-r1-0528-qwen3-8b at 43.9%. It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so claude-opus-4-1-20250805 is 17.8 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
EBR-Bench is a weak spot. claude-opus-4-1-20250805 scores 7.9%, #20 of 21, behind 90% of the models measured. The leader, GPT-6 Astra (max), reaches 76.2%. It covers evidence-based reasoning. The board median is 31.4%, so claude-opus-4-1-20250805 is 23.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
The full table above also lists the other 1 result, including boards with fewer than ten models, where a rank says little.
Strengths and weaknesses
Software engineering: solid, ahead of 59% of the field on average across 3 benchmarks. Its best board here is SWE-bench Verified (#13 of 73) and its weakest is WebDev Arena (#40 of 67). Reasoning, maths and science: solid, ahead of 59% of the field on average across 3 benchmarks. Its best board here is SimpleBench (#9 of 61) and its weakest is OTIS Mock AIME (#113 of 189). General knowledge and chat: solid, ahead of 52% of the field on average across 4 benchmarks. Its best board here is Cybench (#2 of 16) and its weakest is EBR-Bench (#20 of 21).
Release history
The Anthropic model released before it was Claude Sonnet 4 (unknown thinking) on 2025-05-22, which scores 46.1. The next one was claude-opus-4-1-20250805_16K on 2025-08-05, at 49.5.
Reading these numbers
The 11 scores on this page come from 1 source: Epoch AI Benchmarking Hub (11). No official leaderboard supplied any of them, so treat them as third-party measurements.
Models ranked nearby
- #236 Qwen2.5-32B (49.7)
- #237 QwQ-32B (49.7)
- #238 Devstral (2512) (49.7)
- #240 Kimi K2 Thinking (Together) (49.7)
- #241 Frogboss 32B 2510 (49.7)
- #242 claude-sonnet-4-20250514_16K (49.7)
More from Anthropic
- Claude Opus 5.5 (max) (#1, 64.3)
- Claude Fable 5.1 (max) (#3, 61.9)
- Claude Sonnet 5.5 (max) (#4, 60.8)
- Claude Opus 5 (max) (#8, 60.0)
- Claude Fable 5 (max) (#9, 59.9)
- claude-opus-4-8-xhigh-effort (#14, 56.6)
Compare it on the live leaderboard → · How the aggregate score works