Updated daily at 05:00 UTC
Vision-language
Claude Fable 5.1
- Released
- 1 Sep 2026
- Status
- Current
- Context
- 1M
- Max output
- 128K
- Input per 1M tokens
- $10.00
- Output per 1M tokens
- $50.00
- Open weights
- No
- License
- proprietary
- Parameters
- —
- Knowledge cutoff
- Jun 2026
- Reasoning
- Yes
- 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 | 59.5 | 9 | 3 of 4 |
| Coding & software engineering | 62.1 | Not ranked | 2 of 5 |
| Vision & multimodal understanding | 57.1 | Not ranked | 1 of 3 |
| Factuality & hallucination | 70.8 | 4 | 1 of 1 |
| Human preference | 62.4 | 2 | 4 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 | 47.0% | Independent | max | 1 Sep 2026 | Epoch AI |
| DTBench (Decision Theory Benchmark) | Accuracy (capability questions) | 97.6% | Third party | unknown | — | https://conceptualreasoning.ai/dtbench via Epoch AI |
| DTBench (Decision Theory Benchmark) | Accuracy (capability questions) | 97.6% | Third party | xhigh | — | https://conceptualreasoning.ai/dtbench via Epoch AI |
| DTBench (Decision Theory Benchmark) | Accuracy (capability questions) | 97.1% | Third party | medium | — | https://conceptualreasoning.ai/dtbench via Epoch AI |
| DTBench (Decision Theory Benchmark) | Accuracy (capability questions) | 96.5% | Third party | high | — | https://conceptualreasoning.ai/dtbench via Epoch AI |
| DTBench (Decision Theory Benchmark) | Accuracy (capability questions) | 94.1% | Third party | low | — | https://conceptualreasoning.ai/dtbench via Epoch AI |
| Earthborne Rangers (EBR-bench) | Objectives reached | 57.1% | Independent | max | 8 Sep 2026 | Epoch AI |
| LMCA (Language Model Conceptual Argumentation) | Correlation with expert ratings (Pearson r) | 0.6546 | Third party | unknown | — | https://conceptualreasoning.ai/lmca via Epoch AI |
| LMCA (Language Model Conceptual Argumentation) | Correlation with expert ratings (Pearson r) | 0.6532 | Third party | medium | — | https://conceptualreasoning.ai/lmca via Epoch AI |
| LMCA (Language Model Conceptual Argumentation) | Correlation with expert ratings (Pearson r) | 0.6509 | Third party | high | — | https://conceptualreasoning.ai/lmca via Epoch AI |
| LMCA (Language Model Conceptual Argumentation) | Correlation with expert ratings (Pearson r) | 0.6506 | Third party | xhigh | — | https://conceptualreasoning.ai/lmca via Epoch AI |
| LMCA (Language Model Conceptual Argumentation) | Correlation with expert ratings (Pearson r) | 0.6346 | Third party | low | — | https://conceptualreasoning.ai/lmca via Epoch AI |
| Mystery Game Puzzles | Puzzles solved | 58.0% | Independent | max | 1 Sep 2026 | Epoch AI |
Mathematics
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| FrontierMath Tier 4 | Accuracy | 87.8% | Independent | max | 1 Sep 2026 | Epoch AI |
| FrontierMath Tiers 1-3 | Accuracy | 90.2% | Independent | max | 1 Sep 2026 | Epoch AI |
| OTIS Mock AIME 2024-2025 | Accuracy | 100.0% | Independent | max | 1 Sep 2026 | Epoch AI |
Coding & software engineering
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| FrontierCode | Main score (Mean@5) | 50.9% | Third party | medium | — | https://cognition.com/frontiercode via Epoch AI |
| MirrorCode | Score | 73.3% | Independent | high | 10 Sep 2026 | Epoch AI |
| WeirdML (v2) | Average accuracy | 92.9% | Third party | max | — | https://htihle.github.io/weirdml.html via Epoch AI |
| WeirdML (v2) | Average accuracy | 92.3% | Third party | high | — | https://htihle.github.io/weirdml.html via Epoch AI |
Professional knowledge work
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| APEX-Agents | Pass@1 (all rubric criteria met) | 68.6% | Source not stated | unknown | — | Epoch AI via Epoch AI |
| APEX-Agents | Pass@1 (all rubric criteria met) | 59.7% | Source not stated | high | — | Epoch AI via Epoch AI |
Vision & multimodal understanding
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Furniture Assembly | Score | 70.0% | Independent | max | 10 Sep 2026 | Epoch AI |
Factuality & hallucination
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| SimpleQA Verified | Accuracy (% correct) | 70.8% | Independent | max | 1 Sep 2026 | Epoch AI |
Human preference
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Code Arena: WebDev (arena.ai) | Arena score (Elo scale) | 1751 | Independent | max | 25 Sep 2026 | Arena |
| Code Arena: WebDev (arena.ai) | Votes | 5313 | Independent | max | 25 Sep 2026 | Arena |
| Document Arena (arena.ai) | Arena score (Elo scale) | 1493 | Independent | max | 13 Sep 2026 | Arena |
| Document Arena (arena.ai) | Votes | 1403 | Independent | max | 13 Sep 2026 | Arena |
| Text Arena (arena.ai) | Arena score (Elo scale) | 1501 | Independent | max | 25 Sep 2026 | Arena |
| Text Arena (arena.ai) | Votes | 9942 | Independent | max | 25 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Arena score (Elo scale) | 1287 | Independent | max | 28 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Votes | 4050 | Independent | max | 28 Sep 2026 | Arena |
Other Claude Fable versions
- Claude Fable 59 Jun 2026