Mistral Small 4 vs Qwen3.5-9B
Qwen3.5-9B leads Mistral Small 4 on the Artificial Analysis Intelligence Index, 13.3 to 11.3, and Qwen3.5-9B costs 4.0x less per output token ($0.15 vs $0.60 per million). Updated October 21, 2026; 11 benchmarks have a result for both.
Mistral Small 4 or Qwen3.5-9B: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Mistral Small 4 for work measured by Terminal-Bench Hard (Artificial Analysis run) or AA Intelligence Index, where it leads.
- Shared results
- 11
- Mistral Small 4 only
- 4
- Qwen3.5-9B only
- 4
- 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
Qwen3.5-9B
Qwen3.5-9B leads, 13.3 against 11.3.
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
No call
Both take 262K tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3.5-9B
Mistral Small 4 $0.0004, Qwen3.5-9B $0.0002 per turn.
List prices
At a glance
- Coding index
- Mistral Small 4 not benchmarked, Qwen3.5-9B not benchmarked.
- Widest category
- Agentic work, 45.6 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: Mistral Small 4 41.2% against Qwen3.5-9B 86.8%, 45.6 points apart on a 0 to 100 scale.
- Output price
- Mistral Small 4 $0.60 against Qwen3.5-9B $0.15 per million output tokens, 4.0x apart.
- Context window
- Both take 262K tokens.
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 | Qwen3.5-9B | Ties |
|---|---|---|---|---|
| Coding | 2 | 1 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 2 | ||
| General | 0 | 4 | ||
| All shared boards | 2 | 9 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index21
| Benchmark | Mistral Small 4 | Qwen3.5-9B | Leader |
|---|---|---|---|
| AA Coding Index | 26.6 | 23.5 | Mistral Small 4 |
| Vibe Code Bench (Vals AI) | 0.0% | Not measured | Only Mistral Small 4 measured |
| SciCode | 38.8% | 29.5% | Mistral Small 4 |
| Terminal-Bench Hard (Artificial Analysis run) | 17.4% | 24.2% | Qwen3.5-9B |
| Terminal-Bench | Not measured | 9.2% | Only Qwen3.5-9B measured |
| ALE-Bench | 497.6 | Not measured | Only Mistral Small 4 measured |
| Neither model has a result on the other 33 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Mistral Small 4 | Qwen3.5-9B | Leader |
|---|---|---|---|
| AA Intelligence Index | 11.3 | 13.3 | Qwen3.5-9B |
| Epoch Capabilities Index | Not measured | 139.3 | Only Qwen3.5-9B measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Mistral Small 4 | Qwen3.5-9B | Leader |
|---|---|---|---|
| AA Agentic Index | 0.8 | Not measured | Only Mistral Small 4 measured |
| τ²-Bench Telecom | 41.2% | 86.8% | Qwen3.5-9B |
| Neither model has a result on the other 39 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Mistral Small 4 | Qwen3.5-9B | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 76.9% | 80.6% | Qwen3.5-9B |
| Humanity's Last Exam (Artificial Analysis run) | 9.9% | 14.9% | Qwen3.5-9B |
| GPQA Diamond (Epoch AI run) | Not measured | 79.0% | Only Qwen3.5-9B measured |
| Kagi LLM Benchmark | 40.5% | Not measured | Only Mistral Small 4 measured |
| Neither model has a result on the other 18 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Mistral Small 4 | Qwen3.5-9B | Leader |
|---|---|---|---|
| OTIS Mock AIME | Not measured | 61.7% | Only Qwen3.5-9B measured |
| Neither model has a result on the other 12 boards here | |||
KnowledgeNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mistral Small 4 | Qwen3.5-9B | Leader |
|---|---|---|---|
| Neither model has a result on 18 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mistral Small 4 | Qwen3.5-9B | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Mistral Small 4 | Qwen3.5-9B | Leader |
|---|---|---|---|
| IFBench | 48.2% | 66.7% | Qwen3.5-9B |
| Long context reasoning (AA-LCR) | 49.7% | 70.0% | Qwen3.5-9B |
| DTBench | 70.9% | 71.2% | Qwen3.5-9B |
| LMCA | 20.6% | 24.5% | Qwen3.5-9B |
| Neither model has a result on the other 42 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mistral Small 4 | Qwen3.5-9B | 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
Qwen3.5-9B costs less
Repository review
50K input + 3K output tokens
Qwen3.5-9B costs less
Agent loop
200K input + 10K output tokens
Qwen3.5-9B 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 | Qwen3.5-9B |
|---|---|---|
| Maker | Mistral AI | Qwen |
| Weights | Open weights | Open weights |
| Released | March 16, 2026 | March 10, 2026 |
| Context window | 262K | 262K |
| Input $/Mtok | $0.15 | $0.10 |
| Output $/Mtok | $0.60 | $0.15 |
| 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 Qwen3.5-9B for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Mistral Small 4 for work measured by Terminal-Bench Hard (Artificial Analysis run) or AA Intelligence Index, where it leads.
Which is cheaper, Mistral Small 4 or Qwen3.5-9B?
Mistral Small 4 costs $0.15 per million input tokens and $0.60 per million output tokens; Qwen3.5-9B costs $0.10 and $0.15. Cost per solved task is known for neither of them.
Which has the bigger context window, Mistral Small 4 or Qwen3.5-9B?
Neither: both take 262K tokens.
How many benchmarks is the Mistral Small 4 vs Qwen3.5-9B 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 Qwen3.5-9B's on 0. Where only one model has a result, the page says so instead of naming a winner.