Model comparison
MiniMax M3 vs Mistral Medium 3.5 128B
Head-to-head evidence from 21 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Verified leaderboard positions: MiniMax M3 #18; Mistral Medium 3.5 128B unranked
BenchAlign evidence: MiniMax M3 supported; Mistral Medium 3.5 128B not scored. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. MiniMax M3 and Mistral Medium 3.5 128B share 21 comparable benchmark results. 1 of 8 categories are comparable. 24 results are unique to MiniMax M3; 3 to Mistral Medium 3.5 128B.
Updated July 16, 2026- Shared results
- 21
- MiniMax M3 only
- 24
- Mistral Medium 3.5 128B only
- 3
- Comparable categories
- 1 / 8
Pick MiniMax M3 if you want the stronger benchmark profile. Mistral Medium 3.5 128B only becomes the better choice if coding is the priority or you want the stronger reasoning-first profile.
Confidence note. This is a partial-evidence comparison with 21 shared benchmark results across 6 evidence categories; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
MiniMax M3 is clearly ahead on the provisional aggregate, 70 to 61. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Mistral Medium 3.5 128B is also the more expensive model on tokens at $1.50 input / $7.50 output per 1M tokens, versus $0.30 input / $1.20 output per 1M tokens for MiniMax M3. That is roughly 6.3x on output cost alone. Mistral Medium 3.5 128B is the reasoning model in the pair, while MiniMax M3 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. MiniMax M3 gives you the larger context window at 1M, compared with 256K for Mistral Medium 3.5 128B.
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 | MiniMax M3 | Δ | Mistral Medium 3.5 128B |
|---|---|---|---|
| Coding | MiniMax M372.2 | Margin→ 5.4 | Mistral Medium 3.5 128B77.6 |
| Agentic | MiniMax M372.3 | MarginNo overlap | Mistral Medium 3.5 128BNot measured |
| Math | MiniMax M385.7 | MarginNo overlap | Mistral Medium 3.5 128BNot measured |
| Multimodal | MiniMax M364.9 | 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 80.5%B 77.6%Winner: MiniMax M3Δ 2.9SWE-bench Verified: MiniMax M3 scored 80.5%; Mistral Medium 3.5 128B scored 77.6%. MiniMax M3 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | MiniMax M3 | Mistral Medium 3.5 128B | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | MiniMax M3$0.3 input / $1.2 output | Mistral Medium 3.5 128B$1.5 input / $7.5 output | MiniMax M3 has the lower combined listed price. |
| Generation speedtokens per second | MiniMax M3Not available | Mistral Medium 3.5 128BNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | MiniMax M3Not available | Mistral Medium 3.5 128BNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | MiniMax M31M | Mistral Medium 3.5 128B256K | MiniMax M3 lists the larger context window. |
Benchmark Deep Dive
Agentic19 benchmarks
| Benchmark | MiniMax M3 | Mistral Medium 3.5 128B | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 66% | — | Not comparable |
| BrowseCompSource | 83.5% | — | Not comparable |
| OSWorld-VerifiedSource | 70.1% | — | Not comparable |
| MCP AtlasSource | 74.2% | — | Not comparable |
| Claw-EvalSource | 74.5% | — | Not comparable |
| AA Agentic IndexSource | 35.4% | 19.0% | MiniMax M3 leads |
| τ²-bench resultsSource | 88.9% | 94.2% | Mistral Medium 3.5 128B leads |
| GDPval-AASource | 44.7% | 21.4% | MiniMax M3 leads |
| GDPval-AASource | 1395 | 929 | MiniMax M3 leads |
| GDPval rubricsSource | 74.7% | — | Not comparable |
| BankerToolBenchSource | 76.1% | — | Not comparable |
| ResearchClawBenchSource | 19.8% | — | Not comparable |
| OSWorld 2.0Source | 4.6% | — | Not comparable |
| AA BriefcaseSource | 1110 | — | Not comparable |
| AA EnterpriseOps-GymSource | 32.1% | 33.7% | Mistral Medium 3.5 128B leads |
| AA Harvey LABSource | 6.7% | 0.8% | MiniMax M3 leads |
| τ³-bench resultsSource | — | 91.4% | Not comparable |
| Gert LabsSource | — | 39.10% | Not comparable |
| AA Tau3 BankingSource | — | 14.4% | Not comparable |
CodingMistral Medium 3.5 128B wins11 benchmarks
| Benchmark | MiniMax M3 | Mistral Medium 3.5 128B | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 80.5% | 77.6% | MiniMax M3 leads |
| SWE-bench ProSource | 59% | — | Not comparable |
| Terminal-Bench 2.0Source | 66.0% | — | Not comparable |
| NL2RepoSource | 42.1% | — | Not comparable |
| AA Coding IndexSource | 58.6% | 46.9% | MiniMax M3 leads |
| Terminal-Bench HardSource | 42.4% | 33.3% | MiniMax M3 leads |
| AA-SciCodeSource | 45.4% | 39.6% | MiniMax M3 leads |
| VIBE V2Source | 50.1% | — | Not comparable |
| SVG-BenchSource | 63.7% | — | Not comparable |
| KernelBench HardSource | 28.8% | — | Not comparable |
| AA Terminal-Bench 2.1Source | 65.2% | — | Not comparable |
Reasoning2 benchmarks
Knowledge7 benchmarks
| Benchmark | MiniMax M3 | Mistral Medium 3.5 128B | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 44.4% | 29.9% | MiniMax M3 leads |
| AA-GPQA DiamondSource | 92.9% | 74.8% | MiniMax M3 leads |
| AA-HLESource | 37.1% | 12.8% | MiniMax M3 leads |
| AA-Omniscience IndexSource | 1.4% | -36.3% | MiniMax M3 leads |
| AA-Omniscience AccuracySource | 15.0% | 25.1% | Mistral Medium 3.5 128B leads |
| AA-Omniscience Hallucination RateSource | 16.1% | 82.0% | MiniMax M3 leads |
| AA Openness IndexSource | 33.3% | 33.3% | Tie |
Math1 benchmarks
| Benchmark | MiniMax M3 | Mistral Medium 3.5 128B | Result |
|---|---|---|---|
| USAMO 2026Source | 85.7% | — | Not comparable |
Multimodal7 benchmarks
| Benchmark | MiniMax M3 | Mistral Medium 3.5 128B | Result |
|---|---|---|---|
| OfficeQA ProSource | 45.1% | — | Not comparable |
| OmniDocBench 1.5Source | 91.6% | — | Not comparable |
| MMMU-ProSource | 78.1% | — | Not comparable |
| VideoMMMUSource | 84.6% | — | Not comparable |
| Video-MME (with subtitle)Source | 85.4% | — | Not comparable |
| Design Arena WebsiteSource | 1294 | — | Not comparable |
| AA-MMMU-ProSource | 78.6% | 64.9% | MiniMax M3 leads |
Inst. Following1 benchmarks
| Benchmark | MiniMax M3 | Mistral Medium 3.5 128B | Result |
|---|---|---|---|
| AA-IFBenchSource | 82.9% | 68.8% | MiniMax M3 leads |
Frequently Asked Questions (2)
Which is better, MiniMax M3 or Mistral Medium 3.5 128B?
MiniMax M3 is ahead on BenchLM's provisional leaderboard, 70 to 61. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 80.5% and 77.6%.
Which is better for coding, MiniMax M3 or Mistral Medium 3.5 128B?
Mistral Medium 3.5 128B has the edge for coding in this comparison, averaging 77.6 versus 72.2. Inside this category, AA Coding Index is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
The AI models change fast. We track them for you.
A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.