Claude Sonnet 5.5 vs Muse Wonder Full
Vals Science Index?
Sonnet 5.559.1
Muse Wonder Full—
| Benchmark | Sonnet 5.5 | Muse Wonder Full |
|---|---|---|
| Humanity's Last Exam | 45.8 | 53.6 |
| AA Omniscience Index | 21 | 30.2 |
| CritPt (physics) | 24.6 | 32.9 |
| AA Intelligence Index 4.3.2 | 46.8 | 55.8 |
| AA Omniscience · Accuracy | 52 | 43.2 |
| AA Omniscience · Hallucination Rate | 64.6 | 23 |
| AA-LCR (long context) 1.1 | 78 | 83.7 |
| GDP.pdf · AA all-pass | 25.2 | 32.6 |
| Arena Text · overall | 1,475 · xhigh | — |
| Arena Text · Chinese | 1,534.6 · xhigh | — |
| Arena Text · English | 1,485.5 · xhigh | — |
| Arena Text · French | 1,494.6 · xhigh | — |
| Arena Text · instruction following | 1,490.5 · xhigh | — |
| Arena Text · Japanese | 1,459.9 · xhigh | — |
| Arena Text · non-English | 1,455.5 · xhigh | — |
| Arena Text · Russian | 1,458.1 · xhigh | — |
| Arena Text · Spanish | 1,446 · xhigh | — |
| SimpleQA Verified v1 | 46.5 · max | — |
| MLCR-AA | 18.9 | — |
| ARC-AGI-1 · public evaluation | 92.4 | — |
| ARC-AGI-1 · semi-private | 92 | — |
| ARC-AGI-2 · public evaluation | 70.7 | — |
| ARC-AGI-2 · semi-private | 67.4 | — |
| ARC-AGI-3 · semi-private | 1.2 | — |
| Chess Puzzles | 59 · max | — |
| FrontierMath Erdos | 2.9 · max | — |
| FrontierMath Tier 4 (v2) | 80.5 · max | — |
| FrontierMath Tiers 1–3 (v2) | 88.8 · max | — |
| Mystery Game Puzzles | 65 · max | — |
| Vals MedCode | 52.9 | — |
| Vals MedScribe | 91.1 | — |
| Vals Legal Research Bench | 48.1 | — |
| Vals Science Index | 59.1 | — |
Specs
| Spec | Sonnet 5.5 | Muse Wonder Full |
|---|---|---|
| Input, per 1M | $2 | — |
| Output, per 1M | $10 | — |
| Cost per task? | $0.88 | — |
| Speed, tok/s | 106 | — |
| Context | 1M | 1M |
| Weights | Closed | Closed |
| Released | Sep 2026 | Oct 2026 |
| See images | ✓ | ✓ |
| Read PDFs | ✓ | ? |
| Hear audio | — | ✓ |
| Watch video | — | ✓ |
| Call tools | ✓ | ✓ |
| Force a tool call | — | ? |
| Return strict JSON | ✓ | ? |
| Search the web | ✓ | ? |
| Run code | ✓ | ? |
| Use a computer | ✓ | ? |
What breaks when you switch
Sonnet 5.5 → Muse Wonder Full
Only in Muse Code›
Muse Wonder Full requires a Muse Code subscription; max reasoning effort on the Model API Wonder model does not select Full.
Muse Wonder Full → Sonnet 5.5
No forced tool use›
Forced tool_choice any or tool returns HTTP 400; remove the forced choice.
Replace disabled thinking›
Disabled thinking returns HTTP 400; use between_tools for the lowest thinking setting.
No manual thinking budgets›
Manual thinking budgets and extra between_tools fields return HTTP 400; remove manual budgets and send between_tools without display, budget_tokens or block_binding.
Remove sampling parameters›
Non-default temperature, top_p or top_k returns HTTP 400; remove these parameters.
No assistant prefill›
A prefilled final assistant turn returns HTTP 400; remove that prefill.
Old computer tool rejected · Claude API / Google Cloud›
The computer_20251124 tool returns HTTP 400 on the Claude API and Google Cloud; use computer_toolset_20260801 there.