Updated daily at 05:00 UTC
- Released
- 4 Mar 2024
- Status
- Retired
- Retired
- 5 Jan 2026
- Context
- 200K
- Max output
- 4.1K
- Input per 1M tokens
- $15.00
- Output per 1M tokens
- $75.00
- Open weights
- No
- License
- proprietary
- Parameters
- —
- Knowledge cutoff
- Aug 2023
- Reasoning
- No
- Modalities
- text, image → text
Category scores
Out of 100, from independent and third-party results only, by method category-2026-09-29.1.
| Category | Score | Rank | Coverage |
|---|---|---|---|
| Knowledge & reasoning | 9.4 | 97 | 3 of 4 |
| Factuality & hallucination | 12.6 | 65 | 1 of 1 |
| Human preference | 25.7 | Not ranked | 2 of 5 |
Benchmark results
Every result we hold for this model, with who ran it and where it was published.
Knowledge & reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Chess Puzzles | Puzzles solved | 5.0% | Independent | — | 15 Jul 2026 | Epoch AI |
| DTBench (Decision Theory Benchmark) | Accuracy (capability questions) | 61.6% | Third party | — | — | https://conceptualreasoning.ai/dtbench via Epoch AI |
| LMCA (Language Model Conceptual Argumentation) | Correlation with expert ratings (Pearson r) | 0.17 | Third party | — | — | https://conceptualreasoning.ai/lmca via Epoch AI |
| MMLU | Accuracy | 84.6% | Third party | — | — | Stanford CRFM Leaderboard via Epoch AI |
| SimpleBench | Score (AVG@5) | 23.5% | Third party | — | — | SimpleBench Leaderboard via Epoch AI |
| WinoGrande | Accuracy | 88.5% | Self-reported | — | — | The Claude 3 Model Family: Opus, Sonnet, Haiku via Epoch AI |
Scientific reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| GPQA Diamond | Accuracy | 47.2% | Independent | — | 27 Jan 2025 | Epoch AI |
Mathematics
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| MATH Level 5 | Accuracy | 37.5% | Independent | — | 27 Jan 2025 | Epoch AI |
| OTIS Mock AIME 2024-2025 | Accuracy | 4.7% | Independent | — | 25 Feb 2025 | Epoch AI |
Coding & software engineering
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Cybench | Unguided challenges solved | 10.0% | Third party | — | — | Cybench leaderboard via Epoch AI |
| METR Time Horizons | Average task success (Epoch's column) | 29.5% | Third party | — | — | https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/ via Epoch AI |
| WeirdML (v2) | Average accuracy | 19.2% | Third party | — | — | https://htihle.github.io/weirdml.html via Epoch AI |
Factuality & hallucination
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| SimpleQA Verified | Accuracy (% correct) | 12.6% | Independent | — | 31 Aug 2026 | Epoch AI |
Human preference
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Text Arena (arena.ai) | Arena score (Elo scale) | 1322 | Independent | — | 25 Sep 2026 | Arena |
| Text Arena (arena.ai) | Votes | 194909 | Independent | — | 25 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Arena score (Elo scale) | 1062 | Independent | — | 28 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Votes | 15565 | Independent | — | 28 Sep 2026 | Arena |
Other Claude Opus versions
- Claude Opus 5.522 Sep 2026
- Claude Opus 524 Jul 2026
- Claude Opus 4.828 May 2026
- Claude Opus 4.716 Apr 2026
- Claude Opus 4.65 Feb 2026
- Claude Opus 4.524 Nov 2025
- Claude Opus 4.15 Aug 2025
- Claude Opus 422 May 2025