Model comparison
MiniMax M2.7 vs Mistral Large 3
Head-to-head evidence from 15 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: MiniMax M2.7 #36 (Supported); Mistral Large 3 #113 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. MiniMax M2.7 and Mistral Large 3 share 15 comparable benchmark results. 0 of 8 categories are comparable. 20 results are unique to MiniMax M2.7; 1 to Mistral Large 3.
Updated July 23, 2026- Shared results
- 15
- MiniMax M2.7 only
- 20
- Mistral Large 3 only
- 1
- Comparable categories
- 0 / 8
Benchmark data for MiniMax M2.7 and Mistral Large 3 is coming soon on BenchLM.
Confidence note. This is a partial-evidence comparison with 15 shared benchmark results across 5 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.
Mistral Large 3 is priced at $0.50 input / $1.50 output per 1M tokens, versus $0.30 input / $1.20 output per 1M tokens for MiniMax M2.7. MiniMax M2.7 has the larger context window at 200K, compared with 128K for Mistral Large 3.
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 M2.7 | Δ | Mistral Large 3 |
|---|---|---|---|
| Agentic | MiniMax M2.757.0 | MarginNo overlap | Mistral Large 3Not measured |
| Coding | MiniMax M2.753.3 | MarginNo overlap | Mistral Large 3Not measured |
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | MiniMax M2.7 | Mistral Large 3 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | MiniMax M2.7$0.3 input / $1.2 output | Mistral Large 3$0.5 input / $1.5 output | MiniMax M2.7 has the lower combined listed price. |
| Generation speedtokens per second | MiniMax M2.745 tok/s | Mistral Large 348 tok/s | Mistral Large 3 has the higher measured throughput. |
| First-answer latencyseconds to first token | MiniMax M2.72.53 s | Mistral Large 31.04 s | Mistral Large 3 reaches the first token sooner. |
| Context windowmaximum listed tokens | MiniMax M2.7200K | Mistral Large 3128K | MiniMax M2.7 lists the larger context window. |
Benchmark Deep Dive
Agentic11 benchmarks
| Benchmark | MiniMax M2.7 | Mistral Large 3 | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 57% | — | Not comparable |
| τ²-bench resultsSource | 84.8% | 24.6% | MiniMax M2.7 leads |
| ToolathlonSource | 46.3% | — | Not comparable |
| MLE-Bench LiteSource | 66.6% | — | Not comparable |
| MM-ClawBenchSource | 62.7% | — | Not comparable |
| Claw-EvalSource | 48.7% | — | Not comparable |
| AA Agentic IndexSource | 25.6% | 5.5% | MiniMax M2.7 leads |
| APEX-Agents-AASource | 10.6% | — | Not comparable |
| GDPval-AASource | 32.9% | 6.6% | MiniMax M2.7 leads |
| GDPval-AASource | 1158 | 633 | MiniMax M2.7 leads |
| Gert LabsSource | 40.40% | — | Not comparable |
Coding11 benchmarks
| Benchmark | MiniMax M2.7 | Mistral Large 3 | Result |
|---|---|---|---|
| SWE-bench Verified*Source | 75.4% | — | Not comparable |
| SWE-bench ProSource | 56.2% | — | Not comparable |
| SWE-RebenchSource | 51.9% | — | Not comparable |
| SWE MultilingualSource | 76.5% | — | Not comparable |
| Multi-SWE BenchSource | 52.7% | — | Not comparable |
| VIBE-ProSource | 55.6% | — | Not comparable |
| NL2RepoSource | 39.8% | — | Not comparable |
| Vibe Code BenchSource | 27.04% | — | Not comparable |
| React Native EvalsSource | 71.4% | — | Not comparable |
| AA Coding IndexSource | 52.6% | 20.1% | MiniMax M2.7 leads |
| AA-SciCodeSource | 47.0% | 36.2% | MiniMax M2.7 leads |
Reasoning2 benchmarks
Knowledge8 benchmarks
| Benchmark | MiniMax M2.7 | Mistral Large 3 | Result |
|---|---|---|---|
| GPQA-DSource | 87.0% | — | Not comparable |
| MMLU-Pro (Arcee)Source | 80.8% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 38.1% | 15.9% | MiniMax M2.7 leads |
| AA-GPQA DiamondSource | 87.4% | 68.0% | MiniMax M2.7 leads |
| AA-HLESource | 28.1% | 4.1% | MiniMax M2.7 leads |
| AA-Omniscience IndexSource | 0.7% | -39.4% | MiniMax M2.7 leads |
| AA-Omniscience AccuracySource | 26.1% | 24.1% | MiniMax M2.7 leads |
| AA-Omniscience Hallucination RateSource | 34.4% | 83.7% | MiniMax M2.7 leads |
Math1 benchmarks
| Benchmark | MiniMax M2.7 | Mistral Large 3 | Result |
|---|---|---|---|
| AIME25 (Arcee)Source | 80.0% | — | Not comparable |
Multimodal2 benchmarks
Inst. Following1 benchmarks
| Benchmark | MiniMax M2.7 | Mistral Large 3 | Result |
|---|---|---|---|
| AA-IFBenchSource | 75.7% | 36.2% | MiniMax M2.7 leads |
Frequently Asked Questions (3)
Can I compare MiniMax M2.7 and Mistral Large 3 on BenchLM yet?
Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.
Why does this comparison show “coming soon”?
BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.
What data is available for MiniMax M2.7 and Mistral Large 3 today?
MiniMax M2.7: $0.30 input / $1.20 output per 1M tokens Mistral Large 3: $0.50 input / $1.50 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
Related Comparisons
Explore More
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.