Mistral Small 3 vs Qwen2.5 VL 72B Instruct
Mistral Small 3 costs 12.5x less per output token than Qwen2.5 VL 72B Instruct ($0.08 vs $1.00 per million). Updated October 22, 2026; no benchmark has tested both models yet.
- Coding
- No data
- Overall
- No data
- Output $/M
- $0.08
- Coding
- No data
- Overall
- No data
- Output $/M
- $1.00
Mistral Small 3 or Qwen2.5 VL 72B Instruct: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Mistral Small 3 for output tokens 12.5x cheaper ($0.08 vs $1.00 per million).
No benchmark has tested both yet. Mistral Small 3 has results on LiveCodeBench (Artificial Analysis run), LMArena Text: coding and LMArena Text: software and IT; Qwen2.5 VL 72B Instruct on OSWorld, Kagi LLM Benchmark and GeoBench. Compare them on price and context instead.
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
No call
Only Mistral Small 3 has a AA Intelligence Index result, 6.7.
Directional only
Long documents
Listed context window
Qwen2.5 VL 72B Instruct
Qwen2.5 VL 72B Instruct takes 128K tokens against 33K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mistral Small 3
Mistral Small 3 $0.0001, Qwen2.5 VL 72B Instruct $0.0013 per turn.
List prices
At a glance
- Coding index
- Mistral Small 3 not benchmarked, Qwen2.5 VL 72B Instruct not benchmarked.
- Widest category
- None yet: no category has been tested on both models.
- Widest single gap
- None yet: no benchmark has tested both models.
- Output price
- Mistral Small 3 $0.08 against Qwen2.5 VL 72B Instruct $1.00 per million output tokens, 12.5x apart.
- Context window
- Mistral Small 3 takes 33K tokens, Qwen2.5 VL 72B Instruct 128K.
Benchmark by benchmark
Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.
CodingDirectional onlySix of these boards feed the Vibe Coding Index3 boards measured
| Benchmark | Mistral Small 3 | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| LiveCodeBench (Artificial Analysis run) | 25.2% | Not measured | Only Mistral Small 3 measured |
| LMArena Text: coding | 1246 | Not measured | Only Mistral Small 3 measured |
| LMArena Text: software and IT | 1248 | Not measured | Only Mistral Small 3 measured |
| Neither model has a result on the other 36 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | Mistral Small 3 | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| AA Intelligence Index | 6.7 | Not measured | Only Mistral Small 3 measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | Mistral Small 3 | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 19.6% | Not measured | Only Mistral Small 3 measured |
| OSWorld | Not measured | 5.0% | Only Qwen2.5 VL 72B Instruct measured |
| Neither model has a result on the other 39 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index6 boards measured
| Benchmark | Mistral Small 3 | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 46.2% | Not measured | Only Mistral Small 3 measured |
| Humanity's Last Exam (Artificial Analysis run) | 3.8% | Not measured | Only Mistral Small 3 measured |
| LMArena Text: hard prompts | 1233 | Not measured | Only Mistral Small 3 measured |
| LMArena Text: expert | 1202 | Not measured | Only Mistral Small 3 measured |
| LMArena Text: hard prompts in English | 1243 | Not measured | Only Mistral Small 3 measured |
| Kagi LLM Benchmark | Not measured | 36.0% | Only Qwen2.5 VL 72B Instruct measured |
| Neither model has a result on the other 16 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards measured
| Benchmark | Mistral Small 3 | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| AA Math Index | 4.3 | Not measured | Only Mistral Small 3 measured |
| AIME 2025 (Artificial Analysis run) | 4.3% | Not measured | Only Mistral Small 3 measured |
| LMArena Text: math | 1240 | Not measured | Only Mistral Small 3 measured |
| LMArena Text: mathematical work | 1243 | Not measured | Only Mistral Small 3 measured |
| Neither model has a result on the other 9 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index6 boards measured
| Benchmark | Mistral Small 3 | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 65.2% | Not measured | Only Mistral Small 3 measured |
| GeoBench | Not measured | 62.0% | Only Qwen2.5 VL 72B Instruct measured |
| LMArena Text: science | 1235 | Not measured | Only Mistral Small 3 measured |
| LMArena Text: medicine and healthcare | 1215 | Not measured | Only Mistral Small 3 measured |
| LMArena Text: legal and government | 1219 | Not measured | Only Mistral Small 3 measured |
| LMArena Text: business and finance | 1205 | Not measured | Only Mistral Small 3 measured |
| Neither model has a result on the other 12 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index20 boards measured
| Benchmark | Mistral Small 3 | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| IFBench | 26.4% | Not measured | Only Mistral Small 3 measured |
| Long context reasoning (AA-LCR) | 0.0% | Not measured | Only Mistral Small 3 measured |
| LMArena Text | 1234 | Not measured | Only Mistral Small 3 measured |
| LMArena Text: instruction following | 1214 | Not measured | Only Mistral Small 3 measured |
| LMArena Text: creative writing | 1194 | Not measured | Only Mistral Small 3 measured |
| LMArena Vision | Not measured | 1107 | Only Qwen2.5 VL 72B Instruct measured |
| LMArena Text: English | 1256 | Not measured | Only Mistral Small 3 measured |
| LMArena Text: non-English | 1198 | Not measured | Only Mistral Small 3 measured |
| LMArena Text: Chinese | 1204 | Not measured | Only Mistral Small 3 measured |
| LMArena Text: German | 1211 | Not measured | Only Mistral Small 3 measured |
| LMArena Text: Japanese | 1111 | Not measured | Only Mistral Small 3 measured |
| LMArena Text: Korean | 1188 | Not measured | Only Mistral Small 3 measured |
| LMArena Text: French | 1204 | Not measured | Only Mistral Small 3 measured |
| LMArena Text: Russian | 1216 | Not measured | Only Mistral Small 3 measured |
| LMArena Text: multi-turn | 1217 | Not measured | Only Mistral Small 3 measured |
| LMArena Text: longer queries | 1246 | Not measured | Only Mistral Small 3 measured |
| LMArena Text: writing and language | 1214 | Not measured | Only Mistral Small 3 measured |
| LMArena Text: entertainment and media | 1184 | Not measured | Only Mistral Small 3 measured |
| LMArena Vision: English | Not measured | 1115 | Only Qwen2.5 VL 72B Instruct measured |
| LMArena Vision: Chinese | Not measured | 1107 | Only Qwen2.5 VL 72B Instruct measured |
| Neither model has a result on the other 26 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 3 costs less
Repository review
50K input + 3K output tokens
Mistral Small 3 costs less
Agent loop
200K input + 10K output tokens
Mistral Small 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 Small 3 | Qwen2.5 VL 72B Instruct |
|---|---|---|
| Maker | Mistral AI | Qwen |
| Weights | Open weights | Open weights |
| Released | January 30, 2025 | February 1, 2025 |
| Context window | 33K | 128K |
| Input $/Mtok | $0.05 | $0.80 |
| Output $/Mtok | $0.08 | $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 Small 3 better than Qwen2.5 VL 72B Instruct for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Mistral Small 3 for output tokens 12.5x cheaper ($0.08 vs $1.00 per million).
Which is cheaper, Mistral Small 3 or Qwen2.5 VL 72B Instruct?
Mistral Small 3 costs $0.05 per million input tokens and $0.08 per million output tokens; Qwen2.5 VL 72B Instruct costs $0.80 and $1.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Mistral Small 3 or Qwen2.5 VL 72B Instruct?
Qwen2.5 VL 72B Instruct, with 128K tokens against 33K.
Has any benchmark tested both Mistral Small 3 and Qwen2.5 VL 72B Instruct?
No benchmark has tested both yet. Mistral Small 3 has results on LiveCodeBench (Artificial Analysis run), LMArena Text: coding and LMArena Text: software and IT; Qwen2.5 VL 72B Instruct on OSWorld, Kagi LLM Benchmark and GeoBench. Compare them on price and context instead. Data as of October 22, 2026.