claude-opus-4-1-20250805_16K: benchmark scores, price and ranking
claude-opus-4-1-20250805_16K from Anthropic ranks #266 of 743 LLMs on the LLMs Tiger aggregate benchmark score (49.5), based on 5 benchmark results captured up to 2026-10-13.
- Organisation
- Anthropic
- Type
- Frontier model
- Open weights
- No
- Released
- 2025-08-05 (source: name)
- Aggregate rank
- #266 of 743 (score 49.5)
Relative to other models, claude-opus-4-1-20250805_16K is strongest on METR time horizon (#6 of 31) and weakest on ALE-Bench (#45 of 79).
Across the 5 benchmarks where at least ten models are scored, claude-opus-4-1-20250805_16K is in the top 10% on 0 and in the top half on 4.
claude-opus-4-1-20250805_16K benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| METR time horizon | 114 min | #6 of 31 | Epoch AI Benchmarking Hub | 2026-10-13 |
| WeirdML | 45.9% | #37 of 109 | Epoch AI Benchmarking Hub | 2026-10-13 |
| GPQA Diamond | 77.3% | #115 of 275 | Epoch AI Benchmarking Hub | 2026-10-13 |
| OTIS Mock AIME | 64.4% | #89 of 189 | Epoch AI Benchmarking Hub | 2026-10-13 |
| ALE-Bench | 675 | #45 of 79 | Epoch AI Benchmarking Hub | 2026-10-13 |
About claude-opus-4-1-20250805_16K
claude-opus-4-1-20250805_16K 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 5 benchmark results for it across 3 areas, and none is in the top tenth of its board.
Where claude-opus-4-1-20250805_16K stands
On our aggregate score, claude-opus-4-1-20250805_16K is #266 of 743 ranked models, around the middle of the table. Its score is 49.5; the scale is centred on 50, so it sits 0.5 points below the typical model. That beats 64% of the ranked field. Among the 70 ranked Anthropic models it is #45. The next one up is claude-haiku-4-5-20251001_16K at 49.5. The next one down is Claude 3.5 Sonnet at 49.2.
claude-opus-4-1-20250805_16K, benchmark by benchmark
METR time horizon puts claude-opus-4-1-20250805_16K at 114 min, #6 of 31. That beats 81% of the models tested, but 931 minutes short of Claude Mythos Preview (Early) (1,045 min). The results either side are GPT-5 (high) (203 min) and grok-4-0709 (110 min). It covers length of task (minutes) done at 50% success. The board median is 23 min, so claude-opus-4-1-20250805_16K is 91 minutes above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
On WeirdML, claude-opus-4-1-20250805_16K reaches 45.9%. It ranks #37 of 109, ahead of 66% of the field, and 47.4 points behind GPT-6 Astra (max) at 93.3%. The results either side are o1 (high) (46.1%) and grok-4-0709 (45.7%). It covers unusual machine-learning tasks. The board median is 41.2%, so claude-opus-4-1-20250805_16K is 4.7 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
claude-opus-4-1-20250805_16K manages 77.3% on GPQA Diamond, good for #115 of 275. GPT-6 Astra (max) leads at 95.8%, 18.5 points further up, and 58% of models sit below. The results either side are claude-sonnet-4-20250514_32K (78.3%) and NVIDIA-Nemotron-3-Super-120B-A12B-FP8 (77.3%). It covers expert-level science questions. The board median is 71.7%, so claude-opus-4-1-20250805_16K is 5.6 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
OTIS Mock AIME puts claude-opus-4-1-20250805_16K at 64.4%, #89 of 189. That beats 53% of the models tested, but 35.6 points short of Claude Fable 5.1 (max) (100.0%). The results either side are Claude Opus 4 (64.4%) and Qwen3-30B-A3B (62.8%). It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so claude-opus-4-1-20250805_16K is 6.7 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
claude-opus-4-1-20250805_16K lands below the middle on ALE-Bench: 675, #45 of 79, with 56% of the field scoring higher. GPT-6 Astra (max) leads at 2,951; the closest result above is Step 3.7 Flash at 694. It covers AtCoder heuristic-optimisation contests (performance rating). The board median is 764, so claude-opus-4-1-20250805_16K is 89 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Strengths and weaknesses
Reasoning, maths and science: solid, ahead of 56% of the field on average across 2 benchmarks. Its best board here is GPQA Diamond (#115 of 275) and its weakest is OTIS Mock AIME (#89 of 189). General knowledge and chat: solid, ahead of 73% of the field on average across 2 benchmarks. Its best board here is METR time horizon (#6 of 31) and its weakest is WeirdML (#37 of 109).
Release history
The Anthropic model released before it was claude-opus-4-1-20250805 on 2025-08-05, which scores 49.7. The next one was claude-opus-4-1-20250805_27K on 2025-08-05, at 50.7.
Reading these numbers
The 5 scores on this page come from 1 source: Epoch AI Benchmarking Hub (5). No official leaderboard supplied any of them, so treat them as third-party measurements. With 5 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #263 Qwen2.5-Coder-7B-Instruct (49.5)
- #264 Hunyuan-A13B-Instruct (49.5)
- #265 gpt-4o-2024-08-06 (49.5)
- #267 grok-4-fast (49.5)
- #268 Grok 3 mini (49.4)
- #269 GPT-4 (0125) (49.4)
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