Updated daily at 05:00 UTC
- Released
- 2 Sep 2026
- Status
- Current
- Context
- 1M
- Max output
- —
- Input per 1M tokens
- $1.25
- Output per 1M tokens
- $4.25
- Open weights
- No
- License
- proprietary
- Parameters
- —
- Knowledge cutoff
- —
- Reasoning
- Yes
- Modalities
- text, image, video, audio, pdf → 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 | 49.1 | 18 | 2 of 4 |
| Human preference | 59.7 | 6 | 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 | 38.0% | Independent | max | 18 Sep 2026 | Epoch AI |
| Chess Puzzles | Puzzles solved | 35.0% | Independent | xhigh | 16 Sep 2026 | Epoch AI |
| DTBench (Decision Theory Benchmark) | Accuracy (capability questions) | 96.5% | Third party | unknown | — | https://conceptualreasoning.ai/dtbench via Epoch AI |
| LMCA (Language Model Conceptual Argumentation) | Correlation with expert ratings (Pearson r) | 0.5387 | Third party | unknown | — | https://conceptualreasoning.ai/lmca via Epoch AI |
| Mystery Game Puzzles | Puzzles solved | 25.0% | Independent | max | 18 Sep 2026 | Epoch AI |
| Mystery Game Puzzles | Puzzles solved | 14.1% | Independent | xhigh | 16 Sep 2026 | Epoch AI |
Mathematics
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| FrontierMath Tier 4 | Accuracy | 46.3% | Independent | max | 18 Sep 2026 | Epoch AI |
| FrontierMath Tier 4 | Accuracy | 41.5% | Independent | xhigh | 16 Sep 2026 | Epoch AI |
| FrontierMath Tiers 1-3 | Accuracy | 74.4% | Independent | xhigh | 16 Sep 2026 | Epoch AI |
| FrontierMath Tiers 1-3 | Accuracy | 74.0% | Independent | max | 18 Sep 2026 | Epoch AI |
| OTIS Mock AIME 2024-2025 | Accuracy | 99.2% | Independent | xhigh | 17 Sep 2026 | Epoch AI |
Professional knowledge work
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| APEX-Agents | Pass@1 (all rubric criteria met) | 57.8% | Source not stated | unknown | — | Epoch AI via Epoch AI |
Human preference
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Code Arena: WebDev (arena.ai) | Arena score (Elo scale) | 1656 | Independent | max | 25 Sep 2026 | Arena |
| Code Arena: WebDev (arena.ai) | Votes | 5945 | Independent | max | 25 Sep 2026 | Arena |
| Document Arena (arena.ai) | Arena score (Elo scale) | 1468 | Independent | max | 13 Sep 2026 | Arena |
| Document Arena (arena.ai) | Votes | 1006 | Independent | max | 13 Sep 2026 | Arena |
| Text Arena (arena.ai) | Arena score (Elo scale) | 1494 | Independent | max | 25 Sep 2026 | Arena |
| Text Arena (arena.ai) | Votes | 10036 | Independent | max | 25 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Arena score (Elo scale) | 1290 | Independent | max | 28 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Votes | 3472 | Independent | max | 28 Sep 2026 | Arena |
Other Muse Spark versions
- Muse Spark 1.25 Aug 2026
- Muse Spark 1.18 Apr 2026