Model comparison
MAI-Thinking-1 vs Mistral Medium 3.5 128B
Head-to-head evidence from 1 shared benchmark result across 1 category. Overall scores shown here use the public BenchAlign v5 ranking lane.
Evidence parity. MAI-Thinking-1 and Mistral Medium 3.5 128B share 1 comparable benchmark result. 1 of 8 categories are comparable. 12 results are unique to MAI-Thinking-1; 24 to Mistral Medium 3.5 128B.
Updated July 23, 2026- Shared results
- 1
- MAI-Thinking-1 only
- 12
- Mistral Medium 3.5 128B only
- 24
- Comparable categories
- 1 / 8
Treat this as a split decision. MAI-Thinking-1 makes more sense if its workflow fits your team better; Mistral Medium 3.5 128B is the better fit if coding is the priority.
Confidence note. This is a partial-evidence comparison with 1 shared benchmark result across 1 evidence category; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
MAI-Thinking-1 and Mistral Medium 3.5 128B finish on the same BenchAlign overall score, so this is less about a single winner and more about where the edge shows up. The BenchAlign headline says tie; the benchmark table is where the real choice happens.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | MAI-Thinking-1 | Δ | Mistral Medium 3.5 128B |
|---|---|---|---|
| Coding | MAI-Thinking-165.5 | Margin→ 12.1 | Mistral Medium 3.5 128B77.6 |
| Agentic | MAI-Thinking-146.0 | MarginNo overlap | Mistral Medium 3.5 128BNot measured |
| Knowledge | MAI-Thinking-172.5 | MarginNo overlap | Mistral Medium 3.5 128BNot measured |
| Math | MAI-Thinking-189.7 | MarginNo overlap | Mistral Medium 3.5 128BNot measured |
| Inst. Following | MAI-Thinking-185.0 | MarginNo overlap | Mistral Medium 3.5 128BNot measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
SWE-bench Verified
CodingA 73.5%B 77.6%Winner: Mistral Medium 3.5 128BΔ 4.1SWE-bench Verified: MAI-Thinking-1 scored 73.5%; Mistral Medium 3.5 128B scored 77.6%. Mistral Medium 3.5 128B wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | MAI-Thinking-1 | Mistral Medium 3.5 128B | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | MAI-Thinking-1Not available | Mistral Medium 3.5 128B$1.5 input / $7.5 output | A complete price comparison is not available. |
| Generation speedtokens per second | MAI-Thinking-1Not available | Mistral Medium 3.5 128BNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | MAI-Thinking-1Not available | Mistral Medium 3.5 128BNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | MAI-Thinking-1256K | Mistral Medium 3.5 128B256K | Listed context windows are equal. |
Benchmark Deep Dive
Agentic12 benchmarks
| Benchmark | MAI-Thinking-1 | Mistral Medium 3.5 128B | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 46% | — | Not comparable |
| τ³-bench resultsSource | — | 91.4% | Not comparable |
| AA Agentic IndexSource | — | 19.0% | Not comparable |
| τ²-bench resultsSource | — | 94.2% | Not comparable |
| GDPval-AASource | — | 21.4% | Not comparable |
| GDPval-AASource | — | 929 | Not comparable |
| Gert LabsSource | — | 39.10% | Not comparable |
| AA BriefcaseSource | — | 506 | Not comparable |
| AA EnterpriseOps-GymSource | — | 33.7% | Not comparable |
| AA Harvey LABSource | — | 69.1% | Not comparable |
| AA Tau3 BankingSource | — | 14.4% | Not comparable |
| terminalBenchHardSource | — | 33.3% | Not comparable |
CodingMistral Medium 3.5 128B wins5 benchmarks
Reasoning3 benchmarks
Knowledge11 benchmarks
| Benchmark | MAI-Thinking-1 | Mistral Medium 3.5 128B | Result |
|---|---|---|---|
| GPQASource | 84.2% | — | Not comparable |
| GPQA-DSource | 84.2% | — | Not comparable |
| MMLU-ProSource | 85% | — | Not comparable |
| SimpleQASource | 31% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | — | 29.9% | Not comparable |
| AA-GPQA DiamondSource | — | 74.8% | Not comparable |
| AA-HLESource | — | 12.8% | Not comparable |
| AA-Omniscience IndexSource | — | -36.3% | Not comparable |
| AA-Omniscience AccuracySource | — | 25.1% | Not comparable |
| AA-Omniscience Hallucination RateSource | — | 82.0% | Not comparable |
| AA Openness IndexSource | — | 33.3% | Not comparable |
Math3 benchmarks
Multimodal1 benchmarks
| Benchmark | MAI-Thinking-1 | Mistral Medium 3.5 128B | Result |
|---|---|---|---|
| AA-MMMU-ProSource | — | 64.9% | Not comparable |
Frequently Asked Questions (2)
Which is better, MAI-Thinking-1 or Mistral Medium 3.5 128B?
MAI-Thinking-1 and Mistral Medium 3.5 128B are tied on the BenchAlign overall score, so the right pick depends on which category matters most for your use case.
Which is better for coding, MAI-Thinking-1 or Mistral Medium 3.5 128B?
Mistral Medium 3.5 128B has the edge for coding in this comparison, averaging 77.6 versus 65.5. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
Related Comparisons
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.