Mistral Medium 3 vs Qwen2.5 Coder 32B Instruct
Mistral Medium 3 leads Qwen2.5 Coder 32B Instruct on the Artificial Analysis Intelligence Index, 9.0 to 6.7, and Qwen2.5 Coder 32B Instruct costs 2.0x less per output token ($1.00 vs $2.00 per million). Updated October 21, 2026; 28 benchmarks have a result for both.
Mistral Medium 3 or Qwen2.5 Coder 32B Instruct: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Mistral Medium 3 for a larger context window (131K against 33K tokens).
- Shared results
- 28
- Mistral Medium 3 only
- 29
- Qwen2.5 Coder 32B Instruct only
- 7
- Like-for-like categories
- 6 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 Medium 3
Mistral Medium 3 leads, 9.0 against 6.7.
Same board, both measured
Web design
Design Arena: websites
No call
Only Mistral Medium 3 has a Design Arena: websites result, 1079.
Directional only
Long documents
Listed context window
Mistral Medium 3
Mistral Medium 3 takes 131K tokens against 33K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen2.5 Coder 32B Instruct
Mistral Medium 3 $0.0014, Qwen2.5 Coder 32B Instruct $0.0012 per turn.
List prices
At a glance
- Coding index
- Mistral Medium 3 not benchmarked, Qwen2.5 Coder 32B Instruct not benchmarked.
- Widest category
- General, 24.4 points apart on average over 11 shared benchmarks.
- Widest single gap
- LMArena Text: medicine and healthcare: Mistral Medium 3 1381 against Qwen2.5 Coder 32B Instruct 1187, 32.4 points apart on a 0 to 100 scale.
- Output price
- Mistral Medium 3 $2.00 against Qwen2.5 Coder 32B Instruct $1.00 per million output tokens, 2.0x apart.
- Context window
- Mistral Medium 3 takes 131K tokens, Qwen2.5 Coder 32B Instruct 33K.
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 Medium 3 | Bars | Qwen2.5 Coder 32B Instruct | Ties |
|---|---|---|---|---|
| Coding | 3 | 0 | ||
| Intelligence | 2 | 0 | ||
| Reasoning | 5 | 0 | ||
| Math | 2 | 0 | ||
| Knowledge | 5 | 0 | ||
| General | 11 | 0 | ||
| All shared boards | 28 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
| Benchmark | Mistral Medium 3 | Qwen2.5 Coder 32B Instruct | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 16.4% | Only Qwen2.5 Coder 32B Instruct measured |
| SWE-bench Verified | Not measured | 47.0% | Only Qwen2.5 Coder 32B Instruct measured |
| LiveCodeBench (Artificial Analysis run) | 40.0% | 29.5% | Mistral Medium 3 |
| Terminal-Bench Hard (Artificial Analysis run) | 3.8% | Not measured | Only Mistral Medium 3 measured |
| LMArena Text: coding | 1385 | 1276 | Mistral Medium 3 |
| LMArena Text: software and IT | 1385 | 1261 | Mistral Medium 3 |
| Neither model has a result on the other 32 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Mistral Medium 3 | Qwen2.5 Coder 32B Instruct | Leader |
|---|---|---|---|
| AA Intelligence Index | 9.0 | 6.7 | Mistral Medium 3 |
| Epoch Capabilities Index | 134.0 | 119.5 | Mistral Medium 3 |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Mistral Medium 3 | Qwen2.5 Coder 32B Instruct | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 24.3% | Not measured | Only Mistral Medium 3 measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Mistral Medium 3 | Qwen2.5 Coder 32B Instruct | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 57.8% | 41.7% | Mistral Medium 3 |
| Humanity's Last Exam (Artificial Analysis run) | 4.1% | 3.5% | Mistral Medium 3 |
| LMArena Text: hard prompts | 1364 | 1251 | Mistral Medium 3 |
| LMArena Text: expert | 1342 | 1221 | Mistral Medium 3 |
| LMArena Text: hard prompts in English | 1374 | 1269 | Mistral Medium 3 |
| LMArena Vision: diagrams | 1155 | Not measured | Only Mistral Medium 3 measured |
| LMArena Vision: homework | 1165 | Not measured | Only Mistral Medium 3 measured |
| Neither model has a result on the other 14 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Mistral Medium 3 | Qwen2.5 Coder 32B Instruct | Leader |
|---|---|---|---|
| AA Math Index | 30.3 | Not measured | Only Mistral Medium 3 measured |
| AIME 2025 (Artificial Analysis run) | 30.3% | Not measured | Only Mistral Medium 3 measured |
| GSM8K | Not measured | 93.0% | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text: math | 1353 | 1251 | Mistral Medium 3 |
| LMArena Text: mathematical work | 1354 | 1243 | Mistral Medium 3 |
| Neither model has a result on the other 8 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Mistral Medium 3 | Qwen2.5 Coder 32B Instruct | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 76.0% | 63.5% | Mistral Medium 3 |
| MMLU | Not measured | 79.1% | Only Qwen2.5 Coder 32B Instruct measured |
| AI2 Reasoning Challenge | Not measured | 70.5% | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text: science | 1381 | 1221 | Mistral Medium 3 |
| LMArena Text: medicine and healthcare | 1381 | 1187 | Mistral Medium 3 |
| LMArena Text: legal and government | 1384 | 1257 | Mistral Medium 3 |
| LMArena Text: business and finance | 1352 | 1224 | Mistral Medium 3 |
| Neither model has a result on the other 10 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Mistral Medium 3 | Qwen2.5 Coder 32B Instruct | Leader |
|---|---|---|---|
| Design Arena: websites | 1079 | Not measured | Only Mistral Medium 3 measured |
| Design Arena: UI components | 1024 | Not measured | Only Mistral Medium 3 measured |
| Design Arena: game dev | 1018 | Not measured | Only Mistral Medium 3 measured |
| Design Arena: data viz | 1034 | Not measured | Only Mistral Medium 3 measured |
| Design Arena: 3D | 1084 | Not measured | Only Mistral Medium 3 measured |
| Design Arena: all code categories | 1069 | Not measured | Only Mistral Medium 3 measured |
| Neither model has a result on the other 3 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index110
| Benchmark | Mistral Medium 3 | Qwen2.5 Coder 32B Instruct | Leader |
|---|---|---|---|
| IFBench | 39.3% | Not measured | Only Mistral Medium 3 measured |
| Long context reasoning (AA-LCR) | 31.3% | Not measured | Only Mistral Medium 3 measured |
| DTBench | 62.3% | Not measured | Only Mistral Medium 3 measured |
| HellaSwag | Not measured | 83.0% | Only Qwen2.5 Coder 32B Instruct measured |
| WinoGrande | Not measured | 80.8% | Only Qwen2.5 Coder 32B Instruct measured |
| LMArena Text | 1370 | 1230 | Mistral Medium 3 |
| LMArena Text: instruction following | 1338 | 1223 | Mistral Medium 3 |
| LMArena Text: creative writing | 1343 | 1174 | Mistral Medium 3 |
| LMArena Vision | 1157 | Not measured | Only Mistral Medium 3 measured |
| LMArena Text: English | 1385 | 1248 | Mistral Medium 3 |
| LMArena Text: non-English | 1353 | 1205 | Mistral Medium 3 |
| LMArena Text: Chinese | 1374 | 1222 | Mistral Medium 3 |
| LMArena Text: German | 1377 | Not measured | Only Mistral Medium 3 measured |
| LMArena Text: Japanese | 1316 | Not measured | Only Mistral Medium 3 measured |
| LMArena Text: Korean | 1304 | Not measured | Only Mistral Medium 3 measured |
| LMArena Text: French | 1368 | Not measured | Only Mistral Medium 3 measured |
| LMArena Text: Spanish | 1364 | Not measured | Only Mistral Medium 3 measured |
| LMArena Text: Russian | 1359 | 1228 | Mistral Medium 3 |
| LMArena Text: Polish | 1371 | Not measured | Only Mistral Medium 3 measured |
| LMArena Text: multi-turn | 1384 | 1222 | Mistral Medium 3 |
| LMArena Text: longer queries | 1360 | 1251 | Mistral Medium 3 |
| LMArena Text: writing and language | 1352 | 1191 | Mistral Medium 3 |
| LMArena Text: entertainment and media | 1335 | 1150 | Mistral Medium 3 |
| LMArena Vision: English | 1172 | Not measured | Only Mistral Medium 3 measured |
| LMArena Vision: Chinese | 1161 | Not measured | Only Mistral Medium 3 measured |
| LMArena Vision: reading text | 1154 | Not measured | Only Mistral Medium 3 measured |
| LMArena Vision: humor | 1145 | Not measured | Only Mistral Medium 3 measured |
| LMArena Vision: captioning | 1094 | Not measured | Only Mistral Medium 3 measured |
| LMArena Vision: recognizing things | 1141 | Not measured | Only Mistral Medium 3 measured |
| LMArena Vision: creative writing | 1146 | Not measured | Only Mistral Medium 3 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 Medium 3 | Qwen2.5 Coder 32B Instruct | 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
Qwen2.5 Coder 32B Instruct costs less
Repository review
50K input + 3K output tokens
Mistral Medium 3 costs less
Agent loop
200K input + 10K output tokens
Mistral Medium 3 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 Medium 3 | Qwen2.5 Coder 32B Instruct |
|---|---|---|
| Maker | Mistral AI | Qwen |
| Weights | No public weights listed | Open weights |
| Released | May 7, 2025 | November 11, 2024 |
| Context window | 131K | 33K |
| Input $/Mtok | $0.40 | $0.66 |
| Output $/Mtok | $2.00 | $1.00 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Mistral Medium 3 better than Qwen2.5 Coder 32B Instruct for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Mistral Medium 3 for a larger context window (131K against 33K tokens).
Which is cheaper, Mistral Medium 3 or Qwen2.5 Coder 32B Instruct?
Mistral Medium 3 costs $0.40 per million input tokens and $2.00 per million output tokens; Qwen2.5 Coder 32B Instruct costs $0.66 and $1.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Mistral Medium 3 or Qwen2.5 Coder 32B Instruct?
Mistral Medium 3, with 131K tokens against 33K.
How many benchmarks is the Mistral Medium 3 vs Qwen2.5 Coder 32B Instruct comparison based on?
28 benchmarks have a result for both models as of October 21, 2026. Mistral Medium 3's coding index rests on 0 independent benchmarks and Qwen2.5 Coder 32B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.