Mistral Small 4 vs Qwen3.7 Plus
Qwen3.7 Plus leads Mistral Small 4 on the Artificial Analysis Intelligence Index, 25.2 to 11.3, and Mistral Small 4 costs 2.1x less per output token ($0.60 vs $1.28 per million). Updated October 21, 2026; 13 benchmarks have a result for both.
Mistral Small 4 or Qwen3.7 Plus: which to pick
Only Qwen3.7 Plus has a coding score, 33.2 on the Vibe Coding Index; Mistral Small 4 has none, so the two cannot be ranked on coding.
Pick Mistral Small 4 for output tokens 2.1x cheaper ($0.60 vs $1.28 per million).
- Shared results
- 13
- Mistral Small 4 only
- 1
- Qwen3.7 Plus only
- 62
- Like-for-like categories
- 5 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Only Qwen3.7 Plus has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Qwen3.7 Plus
Qwen3.7 Plus leads, 25.2 against 11.3.
Same board, both measured
Agentic work
AA Agentic Index
Qwen3.7 Plus
Qwen3.7 Plus leads, 17.5 against 0.8.
Same board, both measured
Web design
Design Arena: websites
No call
Only Qwen3.7 Plus has a Design Arena: websites result, 1269.
Directional only
Long documents
Listed context window
Qwen3.7 Plus
Qwen3.7 Plus takes 1M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mistral Small 4
Mistral Small 4 $0.0004, Qwen3.7 Plus $0.0010 per turn.
List prices
At a glance
- Coding index
- Mistral Small 4 not benchmarked, Qwen3.7 Plus 33.2 from 2 benchmarks.
- Widest category
- Agentic work, 34.2 points apart on average over 2 shared benchmarks.
- Widest single gap
- τ²-Bench Telecom: Mistral Small 4 41.2% against Qwen3.7 Plus 93.0%, 51.8 points apart on a 0 to 100 scale.
- Output price
- Mistral Small 4 $0.60 against Qwen3.7 Plus $1.28 per million output tokens, 2.1x apart.
- Context window
- Mistral Small 4 takes 262K tokens, Qwen3.7 Plus 1M.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Mistral Small 4 | Bars | Qwen3.7 Plus | Ties |
|---|---|---|---|---|
| Coding | 0 | 4 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 2 | ||
| Reasoning | 0 | 2 | ||
| General | 0 | 4 | ||
| All shared boards | 0 | 13 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
| Benchmark | Mistral Small 4 | Qwen3.7 Plus | Leader |
|---|---|---|---|
| AA Coding Index | 26.6 | 55.9 | Qwen3.7 Plus |
| Vibe Code Bench (Vals AI) | 0.0% | 46.4% | Qwen3.7 Plus |
| Code migration (Vals AI) | Not measured | 12.9% | Only Qwen3.7 Plus measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 52.8% | Only Qwen3.7 Plus measured |
| SkillsBench (Vals AI) | Not measured | 54.3% | Only Qwen3.7 Plus measured |
| SciCode | 38.8% | 46.1% | Qwen3.7 Plus |
| Terminal-Bench Hard (Artificial Analysis run) | 17.4% | 47.0% | Qwen3.7 Plus |
| FrontierCode | Not measured | 10.2% | Only Qwen3.7 Plus measured |
| ALE-Bench | 497.6 | Not measured | Only Mistral Small 4 measured |
| LMArena Text: coding | Not measured | 1473 | Only Qwen3.7 Plus measured |
| LMArena Text: software and IT | Not measured | 1473 | Only Qwen3.7 Plus measured |
| Neither model has a result on the other 27 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Mistral Small 4 | Qwen3.7 Plus | Leader |
|---|---|---|---|
| AA Intelligence Index | 11.3 | 25.2 | Qwen3.7 Plus |
| Epoch Capabilities Index | Not measured | 147.0 | Only Qwen3.7 Plus measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Mistral Small 4 | Qwen3.7 Plus | Leader |
|---|---|---|---|
| AA Agentic Index | 0.8 | 17.5 | Qwen3.7 Plus |
| Finance Agent (Vals AI) | Not measured | 38.2% | Only Qwen3.7 Plus measured |
| Tax Agent Bench (Vals AI) | Not measured | 10.5% | Only Qwen3.7 Plus measured |
| Legal Research Bench (Vals AI) | Not measured | 16.4% | Only Qwen3.7 Plus measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 49.3% | Only Qwen3.7 Plus measured |
| τ²-Bench Telecom | 41.2% | 93.0% | Qwen3.7 Plus |
| OSWorld 2.0 | Not measured | 2.8% | Only Qwen3.7 Plus measured |
| Neither model has a result on the other 32 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Mistral Small 4 | Qwen3.7 Plus | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 76.9% | 90.0% | Qwen3.7 Plus |
| Humanity's Last Exam (Artificial Analysis run) | 9.9% | 35.6% | Qwen3.7 Plus |
| GPQA Diamond (Epoch AI run) | Not measured | 87.9% | Only Qwen3.7 Plus measured |
| Mystery game puzzles | Not measured | 17.0% | Only Qwen3.7 Plus measured |
| LMArena Text: hard prompts | Not measured | 1460 | Only Qwen3.7 Plus measured |
| LMArena Text: expert | Not measured | 1466 | Only Qwen3.7 Plus measured |
| LMArena Text: hard prompts in English | Not measured | 1460 | Only Qwen3.7 Plus measured |
| LMArena Vision: diagrams | Not measured | 1292 | Only Qwen3.7 Plus measured |
| LMArena Vision: homework | Not measured | 1295 | Only Qwen3.7 Plus measured |
| Neither model has a result on the other 12 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | Mistral Small 4 | Qwen3.7 Plus | Leader |
|---|---|---|---|
| OTIS Mock AIME | Not measured | 93.3% | Only Qwen3.7 Plus measured |
| FrontierMath, tiers 1 to 3 | Not measured | 34.4% | Only Qwen3.7 Plus measured |
| LMArena Text: math | Not measured | 1467 | Only Qwen3.7 Plus measured |
| LMArena Text: mathematical work | Not measured | 1470 | Only Qwen3.7 Plus measured |
| Neither model has a result on the other 9 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Mistral Small 4 | Qwen3.7 Plus | Leader |
|---|---|---|---|
| MortgageTax (Vals AI) | Not measured | 66.2% | Only Qwen3.7 Plus measured |
| LMArena Text: science | Not measured | 1464 | Only Qwen3.7 Plus measured |
| LMArena Text: medicine and healthcare | Not measured | 1464 | Only Qwen3.7 Plus measured |
| LMArena Text: legal and government | Not measured | 1451 | Only Qwen3.7 Plus measured |
| LMArena Text: business and finance | Not measured | 1435 | Only Qwen3.7 Plus measured |
| Neither model has a result on the other 12 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Mistral Small 4 | Qwen3.7 Plus | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1269 | Only Qwen3.7 Plus measured |
| Design Arena: UI components | Not measured | 1261 | Only Qwen3.7 Plus measured |
| Design Arena: game dev | Not measured | 1262 | Only Qwen3.7 Plus measured |
| Design Arena: data viz | Not measured | 1276 | Only Qwen3.7 Plus measured |
| Design Arena: 3D | Not measured | 1239 | Only Qwen3.7 Plus measured |
| Design Arena: all code categories | Not measured | 1269 | Only Qwen3.7 Plus measured |
| Design Arena: SVG | Not measured | 1208 | Only Qwen3.7 Plus measured |
| Design Arena: ASCII art | Not measured | 1143 | Only Qwen3.7 Plus measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Mistral Small 4 | Qwen3.7 Plus | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 39.3% | Only Qwen3.7 Plus measured |
| Vals Multimodal Index | Not measured | 53.9% | Only Qwen3.7 Plus measured |
| IFBench | 48.2% | 78.0% | Qwen3.7 Plus |
| Long context reasoning (AA-LCR) | 49.7% | 73.0% | Qwen3.7 Plus |
| DTBench | 70.9% | 84.0% | Qwen3.7 Plus |
| LMCA | 20.6% | 37.6% | Qwen3.7 Plus |
| LMArena Text | Not measured | 1454 | Only Qwen3.7 Plus measured |
| LMArena Text: instruction following | Not measured | 1439 | Only Qwen3.7 Plus measured |
| LMArena Text: creative writing | Not measured | 1438 | Only Qwen3.7 Plus measured |
| LMArena Vision | Not measured | 1278 | Only Qwen3.7 Plus measured |
| LMArena Text: English | Not measured | 1458 | Only Qwen3.7 Plus measured |
| LMArena Text: non-English | Not measured | 1445 | Only Qwen3.7 Plus measured |
| LMArena Text: Chinese | Not measured | 1509 | Only Qwen3.7 Plus measured |
| LMArena Text: German | Not measured | 1471 | Only Qwen3.7 Plus measured |
| LMArena Text: Japanese | Not measured | 1412 | Only Qwen3.7 Plus measured |
| LMArena Text: Korean | Not measured | 1413 | Only Qwen3.7 Plus measured |
| LMArena Text: French | Not measured | 1472 | Only Qwen3.7 Plus measured |
| LMArena Text: Spanish | Not measured | 1457 | Only Qwen3.7 Plus measured |
| LMArena Text: Russian | Not measured | 1457 | Only Qwen3.7 Plus measured |
| LMArena Text: Polish | Not measured | 1449 | Only Qwen3.7 Plus measured |
| LMArena Text: multi-turn | Not measured | 1459 | Only Qwen3.7 Plus measured |
| LMArena Text: longer queries | Not measured | 1454 | Only Qwen3.7 Plus measured |
| LMArena Text: writing and language | Not measured | 1437 | Only Qwen3.7 Plus measured |
| LMArena Text: entertainment and media | Not measured | 1422 | Only Qwen3.7 Plus measured |
| LMArena Vision: English | Not measured | 1280 | Only Qwen3.7 Plus measured |
| LMArena Vision: Chinese | Not measured | 1332 | Only Qwen3.7 Plus measured |
| LMArena Vision: reading text | Not measured | 1288 | Only Qwen3.7 Plus measured |
| LMArena Vision: humor | Not measured | 1261 | Only Qwen3.7 Plus measured |
| LMArena Vision: creative writing | Not measured | 1258 | Only Qwen3.7 Plus measured |
| LMArena Document | Not measured | 1444 | Only Qwen3.7 Plus measured |
| Neither model has a result on the other 16 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mistral Small 4 | Qwen3.7 Plus | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Mistral Small 4 costs less
Repository review
50K input + 3K output tokens
Mistral Small 4 costs less
Agent loop
200K input + 10K output tokens
Mistral Small 4 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Mistral Small 4 | Qwen3.7 Plus |
|---|---|---|
| Maker | Mistral AI | Qwen |
| Weights | Open weights | No public weights listed |
| Released | March 16, 2026 | June 3, 2026 |
| Context window | 262K | 1M |
| Input $/Mtok | $0.15 | $0.32 |
| Output $/Mtok | $0.60 | $1.28 |
| Coding index | Not benchmarked | 33.2 |
| Independent measurements behind it | 1 | 2 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Mistral Small 4 better than Qwen3.7 Plus for coding?
Only Qwen3.7 Plus has a coding score, 33.2 on the Vibe Coding Index; Mistral Small 4 has none, so the two cannot be ranked on coding. Pick Mistral Small 4 for output tokens 2.1x cheaper ($0.60 vs $1.28 per million).
Which is cheaper, Mistral Small 4 or Qwen3.7 Plus?
Mistral Small 4 costs $0.15 per million input tokens and $0.60 per million output tokens; Qwen3.7 Plus costs $0.32 and $1.28. Cost per solved task is known for neither of them.
Which has the bigger context window, Mistral Small 4 or Qwen3.7 Plus?
Qwen3.7 Plus, with 1M tokens against 262K.
How many benchmarks is the Mistral Small 4 vs Qwen3.7 Plus comparison based on?
13 benchmarks have a result for both models as of October 21, 2026. Mistral Small 4's coding index rests on 1 independent benchmark and Qwen3.7 Plus's on 2. Where only one model has a result, the page says so instead of naming a winner.