Across 11 comparable benchmarks, Muse Wonder has better reported results on 11 and worse on 0.
Moderate evidence11 of 11 shared results countedHow we compare
Price basis: Standard rates. The price section below shows the applicable periods.
| Fact | Mistral Medium 3.5 | Muse Wonder |
|---|---|---|
| Context window | 256K tokens | 1M tokens |
| Input / 1M | $1.50 | $4.00 |
| Output / 1M | $7.50 | $20.00 |
| Blended (4:1) | $2.70 | $4.46 |
| Status | Available | Available |
| Released | May 1, 2026 | October 12, 2026 |
Blended is 4:1 input to output with 90% cache hits at listed rates β set your own mix.
Mean of 6 shared benchmarks grouped by capability on a 0β100 scale. How averages are built
Muse Wonder ahead on 2 of 2 counted
Muse Wonder ahead on 1 of 1 counted
Muse Wonder ahead on 1 of 1 counted
No fixed-scale average β see the rows in Benchmark results
Muse Wonder ahead on 1 of 1 counted
Muse Wonder ahead on 5 of 5 counted
No shared comparable results for Abstract reasoning, Computer & tool use, Research & search, Long context, Cybersecurity.
Published scores, with matching modes where available. Gaps show Mistral Medium 3.5 relative to Muse Wonder. Reading the results
| Benchmark | Mistral Medium 3.5 | Muse Wonder | Gap |
|---|---|---|---|
| Code MigrationMaintenance & Optimization Β· Hidden-test pass rate (%) | 5.1Thinking High Β· tools | 62.5β Max Β· tools | β57.4 pts#72 vs #7 of 79 |
| Vibe Code Bench v1.1Code Generation & Editing Β· Pass rate (%) | 2.9Thinking High Β· tools | 83.1β Max Β· tools | β80.2 pts#115 vs #26 of 121 |
| ProofBench v1.1 (Lean 4)Mathematics Β· Accuracy (%) | 9.0Thinking High Β· tools | 84.0β Max Β· tools | β75.0 pts#50 vs #16 of 54 |
| SciCodeScientific Computing Β· Score | 40.2Thinking Β· no tools | 60.3β Max Β· no tools | 0.67Γ#75 vs #10 of 98 |
| GDP.pdfDocuments & Charts Β· Task pass rate (%) | 2.8Thinking Β· no tools | 30.8β Max Β· tools | β28.0 pts#81 vs #7 of 96 |
| AA-BriefcaseOffice & Business Β· AA-Briefcase Elo | 519Normal Β· tools | 1659β Max Β· tools | 0.31Γ#19 vs #9 of 20 |
| EMB (Excel Modeling)Finance Β· Accuracy (%) | 11.2Thinking High Β· tools | 67.1β Max Β· tools | β55.9 pts#76 vs #21 of 78 |
| Finance Agent v2Finance Β· Score | 32.1Thinking High Β· tools | 56.6β Max Β· tools + web | 0.57Γ#67 vs #17 of 75 |
| Legal Research BenchLegal Β· Score | 9.1Thinking High Β· tools | 50.5β Max Β· tools | 0.18Γ#83 vs #8 of 91 |
| Tax Agent BenchFinance Β· Accuracy (%, rubric Γ citation quality) | 4.5Thinking High Β· tools | 36.3β Max Β· tools | β31.8 pts#73 vs #31 of 74 |
| AA Intelligence Index v5.0.1Capability Indices Β· Index (0-100) | 4.6Thinking High Β· tools | 43.6β Max Β· task tools | 0.11Γ#59 vs #17 of 62 |
Maintenance & Optimization Β· Hidden-test pass rate (%)
Code Generation & Editing Β· Pass rate (%)
Mathematics Β· Accuracy (%)
Scientific Computing Β· Score
Documents & Charts Β· Task pass rate (%)
Office & Business Β· AA-Briefcase Elo
Finance Β· Accuracy (%)
Finance Β· Score
Legal Β· Score
Finance Β· Accuracy (%, rubric Γ citation quality)
Capability Indices Β· Index (0-100)
A dash means no result is available.
Time-of-day providers use peak-hour rates; fixed-price providers use standard rates. Off-peak discounts remain in the published details.
Drag the handle above the bar for cache hits, the one below it for the input : output mix Β· 5% steps
Blended price = effective input rate at 90% cache hits Γ 80% + output rate Γ 20%
Mistral Medium 3.5 costs40%lessthan Muse Wonder per million tokens.Using standard rates at this token mix.
Mistral Medium 3.5: Standard pricing. Mistral official pricing verified 2026-11-13; Deprecated 2026-10-31, scheduled retirement 2027-04-30 per docs.mistral.ai/models
Muse Wonder: Standard pricing. Meta Model API; https://dev.meta.ai/models/muse-wonder
| Price / 1M tokens | Mistral Medium 3.5 | Muse Wonder | Ratio |
|---|---|---|---|
| Input | $1.50 | $4.00 | 0.38Γ |
| Output | $7.50 | $20.00 | 0.38Γ |
| Cached input | β | $0.20 | β |
| Cache write | β | β | β |
| Blended | $2.70 | $4.46 | 0.60Γ |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
Reported cost per task, paired with the score from the same run. Settings and sources may differ; costs do not affect the verdict.
Mistral Medium 3.5 relative to Muse Wonder
Summary: 1 of 2 shared benchmarks have matching recorded settings and sources. The average is a geometric mean of 1 positive-cost ratios, one equal weight per benchmark. This benchmark set can include related tests and indexes; it is not a workload cost estimate.
Mistral Medium 3.5 4.4Γ cheaper
Settings or sources differ
Mistral Medium 3.5 4.4Γ cheaper
Settings or sources differ
Effort, protocol, aggregation and source match; other run conditions may differ.
Mistral Medium 3.5
Muse Wonder
Settings or sources differ or are not recorded; interpret the comparison with care.
Mistral Medium 3.5
Muse Wonder
| Benchmark | Mistral Medium 3.5 | Muse Wonder |
|---|---|---|
| AA Coding Agent Index v1.5 | Not reported | |
| AA Coding Agent Index v2.0 | Not reported | |
| AA Intelligence Index v4.3 | Not reported | |
| AA-Briefcase | Not reported | |
| Agent Arena | Not reported | $1.1571 / task Median Β· Net improvement index (percentage points vs. average model): 1.7 Max (With Tools + Internet) |
| Agent Arena Index | Not reported | $1.0919 / task Median Β· Agent Arena Index rating (index points): 1107 Max (With Tools + Internet) |
| Code Migration | Not reported | |
| CritPt | Not reported | |
| CursorBench 4.0 | Not reported | $5.25 / task Average Β· Task score: 50.4 Max (With Tools) Β· cursorbench-4-0-cursor-agent $3.51 / task Average Β· Task score: 46.1 Thinking High (With Tools) Β· cursorbench-4-0-cursor-agent $1.91 / task Average Β· Task score: 41.7 Thinking Low (With Tools) Β· cursorbench-4-0-cursor-agent 3 more settings$2.82 / task Average Β· Task score: 45.2 Thinking Medium (With Tools) Β· cursorbench-4-0-cursor-agent $0.84 / task Average Β· Task score: 34.2 Minimal (With Tools) Β· cursorbench-4-0-cursor-agent $4.24 / task Average Β· Task score: 48.2 Extra-High (With Tools) Β· cursorbench-4-0-cursor-agent |
| EMB (Excel Modeling) | Not reported | |
| FrontierCode 2.0 | Not reported | $3.143 / task Average Β· Weighted rubric score: 24.3 Thinking High (With Tools + Internet) $1.843 / task Average Β· Weighted rubric score: 21.2 Thinking Low (With Tools + Internet) $2.534 / task Average Β· Weighted rubric score: 23.1 Thinking Medium (With Tools + Internet) 1 more settings |
| FrontierCS 2 | Not reported | |
| GDP.pdf | Not reported | |
| GDPval-AA v2 | Not reported | |
| GDPx | Not reported | $15.63 / task Average Β· GDPx β Score: 6.8 Highest (source-reported) (With Tools) Β· overall/score |
| IOI (Vals v2) | Not reported | |
| Legal Research Bench | Not reported | |
| LiveBench 2.0 | Not reported | $1.4088 / task Average Β· Overall score (equal-weight mean of 7 suite scores, 0-100): 78.1 Max (task-specific tools) |
| MysteryMechanism | Not reported | |
| ProofBench v1.1 (Lean 4) | Not reported | |
| Public Benefits Bench v1.1 | Not reported | |
| SciCode | Not reported | |
| Terminal-Bench 4.0 | Not reported | $14.66 / task Average Β· Resolution rate (%): 49.5 Unspecified Reasoning (With Tools) Β· vals-mini-swe |
| Terminal-Bench 4.1 | Not reported | |
| Vals Index v2.2 | Not reported | |
| Vibe Code Bench 1-100 | Not reported | |
| Vibe Code Bench v1.1 | Not reported | |
| WeirdML v3 | Not reported | $10.9871 / task Average Β· Official score (0-1; higher is better): 0.15 Extra-High (With Tools) |
| Attribute | Mistral Medium 3.5 | Muse Wonder |
|---|---|---|
| Availability | Available | Available |
| Provider | MistralAI | Facebook AI Research Lab |
| Model type | Chat model | Reasoning model |
| First release | May 1, 2026 | October 12, 2026 |
| Context window | 256K tokens | 1M tokens |
| Architecture | Undisclosed | Undisclosed |
| Documented capabilities | Coding, Tool use, Function calling, Long context | Reasoning, Coding, Tool use, Function calling, Computer use, Long context, Structured output, Web search |
| Input modalities | Text | Text, Image, Audio, Video |
| Output modalities | Text | Text |
| Weights | Closed / API only | Closed / API only |
| Commercial use | Proprietary | Proprietary |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used Mistral Medium 3.5 or Muse Wonder? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.