Mistral Small 4 vs Qwen3 32B
Mistral Small 4 leads Qwen3 32B on the Artificial Analysis Intelligence Index, 11.3 to 7.3, and Qwen3 32B costs 1.5x less per output token ($0.40 vs $0.60 per million). Updated October 21, 2026; 11 benchmarks have a result for both.
Mistral Small 4 or Qwen3 32B: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Mistral Small 4 for a larger context window (262K against 131K tokens) and work measured by Kagi LLM Benchmark, where it leads.
- Shared results
- 11
- Mistral Small 4 only
- 4
- Qwen3 32B only
- 34
- 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
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Mistral Small 4
Mistral Small 4 leads, 11.3 against 7.3.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Mistral Small 4 has a AA Agentic Index result, 0.8.
Directional only
Long documents
Listed context window
Mistral Small 4
Mistral Small 4 takes 262K tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3 32B
Mistral Small 4 $0.0004, Qwen3 32B $0.0003 per turn.
List prices
At a glance
- Coding index
- Mistral Small 4 not benchmarked, Qwen3 32B not benchmarked.
- Widest category
- General, 17.1 points apart on average over 4 shared benchmarks.
- Widest single gap
- Long context reasoning (AA-LCR): Mistral Small 4 49.7% against Qwen3 32B 0.0%, 49.7 points apart on a 0 to 100 scale.
- Output price
- Mistral Small 4 $0.60 against Qwen3 32B $0.40 per million output tokens, 1.5x apart.
- Context window
- Mistral Small 4 takes 262K tokens, Qwen3 32B 131K.
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 32B | Ties |
|---|---|---|---|---|
| Coding | 2 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 2 | 1 | ||
| General | 4 | 0 | ||
| All shared boards | 10 | 1 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
| Benchmark | Mistral Small 4 | Qwen3 32B | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 40.0% | Only Qwen3 32B measured |
| AA Coding Index | 26.6 | Not measured | Only Mistral Small 4 measured |
| Vibe Code Bench (Vals AI) | 0.0% | Not measured | Only Mistral Small 4 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 54.6% | Only Qwen3 32B measured |
| SciCode | 38.8% | 36.0% | Mistral Small 4 |
| Terminal-Bench Hard (Artificial Analysis run) | 17.4% | 3.0% | Mistral Small 4 |
| ALE-Bench | 497.6 | Not measured | Only Mistral Small 4 measured |
| LMArena Text: coding | Not measured | 1357 | Only Qwen3 32B measured |
| LMArena Text: software and IT | Not measured | 1366 | Only Qwen3 32B measured |
| Neither model has a result on the other 30 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Mistral Small 4 | Qwen3 32B | Leader |
|---|---|---|---|
| AA Intelligence Index | 11.3 | 7.3 | Mistral Small 4 |
| Epoch Capabilities Index | Not measured | 138.4 | Only Qwen3 32B measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Mistral Small 4 | Qwen3 32B | Leader |
|---|---|---|---|
| AA Agentic Index | 0.8 | Not measured | Only Mistral Small 4 measured |
| τ²-Bench Telecom | 41.2% | 29.8% | Mistral Small 4 |
| Berkeley Function Calling Leaderboard (BFCL) | Not measured | 48.7% | Only Qwen3 32B measured |
| BrowseComp-Plus | Not measured | 10.7% | Only Qwen3 32B measured |
| Neither model has a result on the other 37 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | Mistral Small 4 | Qwen3 32B | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 76.9% | 66.8% | Mistral Small 4 |
| Humanity's Last Exam (Artificial Analysis run) | 9.9% | 7.4% | Mistral Small 4 |
| GPQA Diamond (Epoch AI run) | Not measured | 65.7% | Only Qwen3 32B measured |
| LMArena Text: hard prompts | Not measured | 1334 | Only Qwen3 32B measured |
| LMArena Text: expert | Not measured | 1362 | Only Qwen3 32B measured |
| LMArena Text: hard prompts in English | Not measured | 1350 | Only Qwen3 32B measured |
| Kagi LLM Benchmark | 40.5% | 48.7% | Qwen3 32B |
| Neither model has a result on the other 15 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Mistral Small 4 | Qwen3 32B | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 73.0 | Only Qwen3 32B measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 73.0% | Only Qwen3 32B measured |
| OTIS Mock AIME | Not measured | 66.9% | Only Qwen3 32B measured |
| LMArena Text: math | Not measured | 1399 | Only Qwen3 32B measured |
| LMArena Text: mathematical work | Not measured | 1420 | Only Qwen3 32B measured |
| Neither model has a result on the other 8 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Mistral Small 4 | Qwen3 32B | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | Not measured | 79.8% | Only Qwen3 32B measured |
| LMArena Text: science | Not measured | 1372 | Only Qwen3 32B measured |
| LMArena Text: medicine and healthcare | Not measured | 1368 | Only Qwen3 32B measured |
| LMArena Text: legal and government | Not measured | 1324 | Only Qwen3 32B measured |
| LMArena Text: business and finance | Not measured | 1318 | Only Qwen3 32B measured |
| Neither model has a result on the other 13 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mistral Small 4 | Qwen3 32B | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Mistral Small 4 | Qwen3 32B | Leader |
|---|---|---|---|
| IFBench | 48.2% | 36.3% | Mistral Small 4 |
| Long context reasoning (AA-LCR) | 49.7% | 0.0% | Mistral Small 4 |
| DTBench | 70.9% | 67.5% | Mistral Small 4 |
| LMCA | 20.6% | 17.3% | Mistral Small 4 |
| Fiction.LiveBench | Not measured | 74.2% | Only Qwen3 32B measured |
| LMArena Text | Not measured | 1340 | Only Qwen3 32B measured |
| LMArena Text: instruction following | Not measured | 1305 | Only Qwen3 32B measured |
| LMArena Text: creative writing | Not measured | 1297 | Only Qwen3 32B measured |
| LMArena Text: English | Not measured | 1359 | Only Qwen3 32B measured |
| LMArena Text: non-English | Not measured | 1317 | Only Qwen3 32B measured |
| LMArena Text: Chinese | Not measured | 1357 | Only Qwen3 32B measured |
| LMArena Text: German | Not measured | 1341 | Only Qwen3 32B measured |
| LMArena Text: Russian | Not measured | 1311 | Only Qwen3 32B measured |
| LMArena Text: multi-turn | Not measured | 1331 | Only Qwen3 32B measured |
| LMArena Text: longer queries | Not measured | 1327 | Only Qwen3 32B measured |
| LMArena Text: writing and language | Not measured | 1298 | Only Qwen3 32B measured |
| LMArena Text: entertainment and media | Not measured | 1279 | Only Qwen3 32B measured |
| Neither model has a result on the other 29 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mistral Small 4 | Qwen3 32B | 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
Qwen3 32B costs less
Repository review
50K input + 3K output tokens
Qwen3 32B costs less
Agent loop
200K input + 10K output tokens
Qwen3 32B 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 32B |
|---|---|---|
| Maker | Mistral AI | Qwen |
| Weights | Open weights | Open weights |
| Released | March 16, 2026 | April 28, 2025 |
| Context window | 262K | 131K |
| Input $/Mtok | $0.15 | $0.14 |
| Output $/Mtok | $0.60 | $0.40 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 1 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Mistral Small 4 better than Qwen3 32B for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Mistral Small 4 for a larger context window (262K against 131K tokens) and work measured by Kagi LLM Benchmark, where it leads.
Which is cheaper, Mistral Small 4 or Qwen3 32B?
Mistral Small 4 costs $0.15 per million input tokens and $0.60 per million output tokens; Qwen3 32B costs $0.14 and $0.40. Cost per solved task is known for neither of them.
Which has the bigger context window, Mistral Small 4 or Qwen3 32B?
Mistral Small 4, with 262K tokens against 131K.
How many benchmarks is the Mistral Small 4 vs Qwen3 32B comparison based on?
11 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 32B's on 0. Where only one model has a result, the page says so instead of naming a winner.