Muse Wonder
| Released | 2026-10-12 |
|---|---|
| Price per 1M | $4.00 in · $20.00 out |
| Overall score | 63.0 · rank 12 |
| Context window | 1,048,576 tokens |
| Provider | Meta |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 63.0 | 12 | 40 |
| Overall: Coding | 62.2 | 15 | 30 |
| Overall: Reasoning | 63.3 | 15 | 12 |
| Overall: Agentic work | 62.7 | 11 | 27 |
| Overall: Frontend | 59.9 | 23 | 11 |
| Coding | 62.8 | 12 | 8 |
| Agents | 62.4 | 12 | 12 |
| Reasoning | 63.8 | 20 | 7 |
| Math | 62.8 | 17 | 4 |
| Knowledge | 63.2 | 12 | 1 |
| Frontend | 58.5 | 35 | 3 |
| General | 65.3 | 7 | 5 |
| Value vs price | +9.0 | 36 |
Buzz
| Posts on X | About 70 a day |
|---|---|
| Mood | 37% positive, 16% negative |
| Hacker News | 3 mentions this week |
| Checked | 2026-11-11 |
- On top of making every inference call cheaper, distilled models are also significantly faster, which unlocks a lot more. Muse Ember for instance: 1. ~450 tokens/sec on Artificial Analysis. That’s almost 2x Haiku 5.5 at the same intelligence score, and ~3.5x Muse Wonder (disclai…
- 🚀 25 AI tools everyone is talking about in November 2026. Ranked by their buzz on X. Whether you're a developer, designer, content creator, or someone exploring AI, here are 25 tools worth knowing: 1. Claude – Long-context writing and thoughtful coding assistance. 2. ChatGPT…
- Gamefeel RE subsection: Muse Ember and Muse wonder max added they perform so poorly and it was so expensive to run that I dont feel like there is any point running all the other subsections https://t.co/A4kmlJohtV
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 63.7 ±2.0 | 11 |
| High | 63.0 ±3.5 | 4 |
| Low | 60.6 ±5.0 | 1 |
| Max | 62.8 ±1.1 | 26 |
| Medium | 61.9 ±5.0 | 1 |
| Minimal | 57.7 ±5.0 | 1 |
| Extra High | 62.7 ±4.9 | 2 |
Evidence
Coding 62.8 ±1.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| CursorBench | 50.4% | Epoch AI | 2026-11-11 |
| Code Migration v1.1 | 72.4% | Vals AI | 2026-11-09 |
| LiveBench 2.0 Coding | 74.9% | LiveBench | 2026-11-06 |
| WeirdML v3 | 15.2% | Epoch AI | 2026-11-11 |
| MirrorCode | 45.6% | Epoch AI | 2026-10-14 |
| IOI | 66.9% | Vals AI | 2026-10-29 |
| SWE-bench Multimodal | 45.6% | Vals AI | 2026-11-09 |
| SciCode | 60.3% | Epoch AI | 2026-11-11 |
Agents 62.4 ±1.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 4.0 (Vals run) | 49.5% | Vals AI | 2026-11-09 |
| Terminal-Bench-Science | 22.9% | Vals AI | 2026-11-09 |
| APEX-Agents | 66.1% | Epoch AI | 2026-11-11 |
| LiveBench 2.0 Agentic | 46.2% | LiveBench | 2026-11-06 |
| LiveBench 2.0 Browser Use | 60.0% | LiveBench | 2026-11-06 |
| EMB v1.1 (Excel financial modeling) | 72.5% | Vals AI | 2026-11-09 |
| LiveBench 2.0 Research | 93.0% | LiveBench | 2026-11-06 |
| Tax Agent Bench | 36.3% | Vals AI | 2026-11-09 |
| Finance Agent v2.1 | 65.5% | Vals AI | 2026-11-09 |
| Vending-Bench 2 | $9,432 | Epoch AI | 2026-11-11 |
| HLAB-Vals 1.1 (legal agent) | 23.8% | Vals AI | 2026-11-09 |
| CyberBench v1.1 | 80.4% | Vals AI | 2026-11-05 |
Reasoning 63.8 ±2.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Extended NYT Connections | 93.4% | Lech Mazur | 2026-11-10 |
| MysteryMechanism | 27.5% | Vals AI | 2026-11-09 |
| CritPt | 28.3% | Epoch AI | 2026-11-11 |
| BioMysteryBench | 67.0% | Vals AI | 2026-11-09 |
| LiveBench 2.0 Reasoning | 90.6% | LiveBench | 2026-11-06 |
| Mystery Game Puzzles | 51.0% | Epoch AI | 2026-10-14 |
| LiveBench 2.0 Data Analysis | 81.6% | LiveBench | 2026-11-06 |
Math 62.8 ±1.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 82.1% | Epoch AI | 2026-10-12 |
| FrontierMath Tier 4 | 70.7% | Epoch AI | 2026-10-12 |
| OTIS Mock AIME 2024-2025 | 99.4% | Epoch AI | 2026-10-12 |
| ProofBench v1.1 | 84.0% | Vals AI | 2026-11-09 |
| ProofBench | 84.0% | Epoch AI | 2026-11-11 |
Knowledge 63.2 ±6.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Legal Research Bench | 50.5% | Vals AI | 2026-11-09 |
Frontend 58.5 ±2.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LiveBench 2.0 Design | 70.9% | LiveBench | 2026-11-06 |
| Vibe Code Bench v1.1 | 83.1% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,650 | LMArena | 2026-11-09 |
General 65.3 ±1.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LLM Debate Benchmark | 1,647 | Lech Mazur | 2026-10-26 |
| EQ-Bench 4 | 1,325 | EQ-Bench | 2026-10-24 |
| EQ-Bench Creative Writing v3 | 2,007 | EQ-Bench | 2026-11-11 |
| LMArena Text | 1,511 | LMArena | 2026-11-09 |
| Creative Story-Writing (Lech Mazur) | 76.0% | Lech Mazur | 2026-10-23 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| CursorBench | 48.2% | Epoch AI | A stronger configuration result was used |
| CursorBench | 46.1% | Epoch AI | A stronger configuration result was used |
| CursorBench | 45.2% | Epoch AI | A stronger configuration result was used |
| CursorBench | 41.7% | Epoch AI | A stronger configuration result was used |
| CursorBench | 34.2% | Epoch AI | A stronger configuration result was used |
Names matched to this model
muse-wonder, muse-wonder-1-0