Model comparison
Granite 4.0 Micro vs Mistral Small 3
Mistral Small 3 is the stronger model overall, scoring 31.2 to 29.0 on the Noometry Index.
Last verified . 3 shared benchmarks.
Mistral AISummary
- They share 3 benchmarks with published results for both. Granite 4.0 Micro scores higher in 3 categories and Mistral Small 3 in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Small 3 leads 25.1 to 9.9.
- The biggest single-benchmark swing is GPQA Diamond: 28.3% for Granite 4.0 Micro and 47.3% for Mistral Small 3.
- Granite 4.0 Micro is cheaper at $0.017 / $0.11 per million input/output tokens, against $0.05 / $0.08 for Mistral Small 3.
- Granite 4.0 Micro accepts more context: 131K tokens versus 33K.
Side by side
| Granite 4.0 Micro | Mistral Small 3 | |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 29.0 | 31.2 |
| Released | 2025-10-02 | 2025-01-30 |
| Weights | Open | Open |
| Context window | 131K | 33K |
| Max output | 118K | 16K |
| Input $ / M tokens | $0.017 | $0.05 |
| Output $ / M tokens | $0.11 | $0.08 |
| Results tracked | 8 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Granite 4.0 Micro: —, Mistral Small 3: 36.5 (#207)
| Benchmark | Granite 4.0 Micro | Mistral Small 3 |
|---|---|---|
| BigCodeBench Instruct | — | 45.3% |
| LMArena Coding | — | 1246 |
| BigCodeBench Complete | — | 50.4% |
Reasoning Too close to call
Granite 4.0 Micro: 19.2 (#265), Mistral Small 3: 18.9 (#273)
| Benchmark | Granite 4.0 Micro | Mistral Small 3 |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| LMArena Hard Prompts | — | 1233 |
| Epoch Capabilities Index | — | 127.07 |
Math Mistral Small 3 leads
Granite 4.0 Micro: 12.0 (#307), Mistral Small 3: 16.3 (#295)
| Benchmark | Granite 4.0 Micro | Mistral Small 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.8% | 6.7% |
| Omni-MATH | 20.9% | — |
| LMArena Math | — | 1240 |
Knowledge Mistral Small 3 leads
Granite 4.0 Micro: 9.9 (#304), Mistral Small 3: 25.1 (#263)
| Benchmark | Granite 4.0 Micro | Mistral Small 3 |
|---|---|---|
| GPQA Diamond | 28.3% | 47.3% |
| MMLU-Pro | 39.5% | — |
| Confabulations | — | 25.2% |
| GPQA (HELM) | 30.7% | — |
| LMArena Expert | — | 1202 |
Multilingual Not comparable
Granite 4.0 Micro: —, Mistral Small 3: 37.3 (#236)
| Benchmark | Granite 4.0 Micro | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | — | 1198 |
| LMArena Chinese | — | 1204 |
| LMArena French | — | 1203 |
| LMArena German | — | 1211 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1188 |
| LMArena Russian | — | 1216 |
Instruction Following Granite 4.0 Micro leads
Granite 4.0 Micro: 69.9 (#169), Mistral Small 3: 63.7 (#229)
| Benchmark | Granite 4.0 Micro | Mistral Small 3 |
|---|---|---|
| IFEval | 84.9% | — |
| LMArena Instruction Following | — | 1214 |
Long Context Not comparable
Granite 4.0 Micro: —, Mistral Small 3: 37.8 (#211)
| Benchmark | Granite 4.0 Micro | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | — | 1246 |
Writing & Preference Granite 4.0 Micro leads
Granite 4.0 Micro: 46.7 (#216), Mistral Small 3: 32.2 (#280)
| Benchmark | Granite 4.0 Micro | Mistral Small 3 |
|---|---|---|
| LMArena Text | — | 1234 |
| LMArena Creative Writing | — | 1195 |
| EQ-Bench Creative Writing | — | 707 |
| WildBench | 67% | — |
| LMArena Multi-Turn | — | 1217 |
Frequently asked questions
Is Granite 4.0 Micro better than Mistral Small 3?
Mistral Small 3 is the stronger model overall, scoring 31.2 to 29.0 on the Noometry Index.
Which is cheaper, Granite 4.0 Micro or Mistral Small 3?
Granite 4.0 Micro is cheaper. It lists at $0.017 per million input tokens and $0.11 per million output tokens; Mistral Small 3 lists at $0.05 and $0.08.
Which has the bigger context window?
Granite 4.0 Micro does, with 131K tokens against 33K.
How many benchmarks do Granite 4.0 Micro and Mistral Small 3 share?
3 benchmarks have published results for both models. Granite 4.0 Micro has 8 scored results on Noometry and Mistral Small 3 has 24.