Model comparison
Mistral Small 4 vs Qwen3.7 Max
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: Mistral Small 4 #140 (Estimated); Qwen3.7 Max #10 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Mistral Small 4 and Qwen3.7 Max share 15 comparable benchmark results. 0 of 8 categories are comparable. 1 result is unique to Mistral Small 4; 43 to Qwen3.7 Max.
Updated July 23, 2026- Shared results
- 15
- Mistral Small 4 only
- 1
- Qwen3.7 Max only
- 43
- Comparable categories
- 0 / 8
Benchmark data for Mistral Small 4 and Qwen3.7 Max 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.
Qwen3.7 Max has the larger context window at 1M, compared with 256K for Mistral Small 4.
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 | Mistral Small 4 | Δ | Qwen3.7 Max |
|---|---|---|---|
| Agentic | Mistral Small 4Not measured | MarginNo overlap | Qwen3.7 Max69.7 |
| Coding | Mistral Small 4Not measured | MarginNo overlap | Qwen3.7 Max77.9 |
| Reasoning | Mistral Small 4Not measured | MarginNo overlap | Qwen3.7 Max90.4 |
| Knowledge | Mistral Small 4Not measured | MarginNo overlap | Qwen3.7 Max64.2 |
| Math | Mistral Small 4Not measured | MarginNo overlap | Qwen3.7 Max97.1 |
| Multilingual | Mistral Small 4Not measured | MarginNo overlap | Qwen3.7 Max87.0 |
| Inst. Following | Mistral Small 4Not measured | MarginNo overlap | Qwen3.7 Max84.4 |
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Mistral Small 4 | Qwen3.7 Max | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Mistral Small 4$0.15 input / $0.6 output | Qwen3.7 MaxNot available | A complete price comparison is not available. |
| Generation speedtokens per second | Mistral Small 4175 tok/s | Qwen3.7 MaxNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Mistral Small 40.64 s | Qwen3.7 MaxNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Mistral Small 4256K | Qwen3.7 Max1M | Qwen3.7 Max lists the larger context window. |
Benchmark Deep Dive
Agentic21 benchmarks
| Benchmark | Mistral Small 4 | Qwen3.7 Max | Result |
|---|---|---|---|
| AA Agentic IndexSource | 4.7% | 30.6% | Qwen3.7 Max leads |
| τ²-bench resultsSource | 41.2% | 94.7% | Qwen3.7 Max leads |
| GDPval-AASource | 4.4% | 38.7% | Qwen3.7 Max leads |
| GDPval-AASource | 588 | 1273 | Qwen3.7 Max leads |
| Terminal-Bench 2.0Source | — | 69.7% | Not comparable |
| QwenClawBenchSource | — | 64.3% | Not comparable |
| QwenWebBenchSource | — | 1568 | Not comparable |
| Claw-EvalSource | — | 65.2% | Not comparable |
| BFCL v4Source | — | 75.0% | Not comparable |
| MCP AtlasSource | — | 76.4% | Not comparable |
| VITA-BenchSource | — | 47.9% | Not comparable |
| HLE w/ toolsSource | — | 53.5% | Not comparable |
| Gert LabsSource | — | 64.27% | Not comparable |
| ResearchClawBenchSource | — | 18.7% | Not comparable |
| AA BriefcaseSource | — | 908 | Not comparable |
| AA AutomationBenchSource | — | 25.6% | Not comparable |
| AA EnterpriseOps-GymSource | — | 45.0% | Not comparable |
| AA ITBenchSource | — | 42.5% | Not comparable |
| terminalBenchHardSource | — | 50.8% | Not comparable |
| aaTerminalBench21Source | — | 74.5% | Not comparable |
| AA Harvey LABSource | — | 83.4% | Not comparable |
Coding9 benchmarks
| Benchmark | Mistral Small 4 | Qwen3.7 Max | Result |
|---|---|---|---|
| AA Coding IndexSource | 26.6% | 66.0% | Qwen3.7 Max leads |
| AA-SciCodeSource | 38.0% | 48.8% | Qwen3.7 Max leads |
| SWE-bench VerifiedSource | — | 80.4% | Not comparable |
| SWE-bench ProSource | — | 60.6% | Not comparable |
| SWE MultilingualSource | — | 78.3% | Not comparable |
| NL2RepoSource | — | 47.2% | Not comparable |
| SciCodeSource | — | 53.5% | Not comparable |
| LiveCodeBenchSource | — | 91.6% | Not comparable |
| Terminal-Bench 2.0Source | — | 69.7% | Not comparable |
Reasoning3 benchmarks
Knowledge13 benchmarks
| Benchmark | Mistral Small 4 | Qwen3.7 Max | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 19.6% | 46.0% | Qwen3.7 Max leads |
| AA-GPQA DiamondSource | 76.9% | 92.3% | Qwen3.7 Max leads |
| AA-HLESource | 9.5% | 38.1% | Qwen3.7 Max leads |
| AA-Omniscience IndexSource | -29.9% | 14.1% | Qwen3.7 Max leads |
| AA-Omniscience AccuracySource | 22.1% | 30.1% | Qwen3.7 Max leads |
| AA-Omniscience Hallucination RateSource | 66.8% | 22.9% | Qwen3.7 Max leads |
| GPQASource | — | 92.4% | Not comparable |
| GPQA-DSource | — | 92.4% | Not comparable |
| HLESource | — | 41.4% | Not comparable |
| MMLU-ProSource | — | 89.6% | Not comparable |
| MMLU-ReduxSource | — | 95% | Not comparable |
| SuperGPQASource | — | 73.6% | Not comparable |
| MMMLUSource | — | 90.3% | Not comparable |
Math3 benchmarks
Multilingual5 benchmarks
Multimodal2 benchmarks
Frequently Asked Questions (3)
Can I compare Mistral Small 4 and Qwen3.7 Max 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 Mistral Small 4 and Qwen3.7 Max today?
Mistral Small 4: $0.15 input / $0.60 output per 1M tokens Qwen3.7 Max: Pricing unavailable 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.