Model comparison
Gemma 4 31B IT vs Mistral Small
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 33.4 on the Noometry Index.
Last verified . 24 shared benchmarks.
Google
Mistral AISummary
- They share 24 benchmarks with published results for both. Gemma 4 31B IT scores higher in 9 categories and Mistral Small in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 4 31B IT leads 43.2 to 16.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 73.3% for Gemma 4 31B IT and 5.8% for Mistral Small.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.15 / $0.60 for Mistral Small.
Side by side
| Gemma 4 31B IT | Mistral Small | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 43.5 | 33.4 |
| Released | 2026-04-02 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 33K | 256K |
| Input $ / M tokens | $0.09 | $0.15 |
| Output $ / M tokens | $0.34 | $0.60 |
| Results tracked | 35 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 31B IT leads
Gemma 4 31B IT: 42.3 (#108), Mistral Small: 34.0 (#247)
| Benchmark | Gemma 4 31B IT | Mistral Small |
|---|---|---|
| SciCode | 43.4% | 26.5% |
| LMArena Coding | 1459 | 1362 |
| ALE-Bench | 925.5 | 497.62 |
| LMArena WebDev | 1366 | — |
| WeirdML | 52.3% | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
Agentic & Tool Use Not comparable
Gemma 4 31B IT: —, Mistral Small: 28.1 (#93)
| Benchmark | Gemma 4 31B IT | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
Reasoning Gemma 4 31B IT leads
Gemma 4 31B IT: 27.2 (#122), Mistral Small: 19.8 (#250)
| Benchmark | Gemma 4 31B IT | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | 63.5% | 37.8% |
| CritPt | 1.4% | 0% |
| LMArena Hard Prompts | 1448 | 1335 |
| DTBench | 82.7% | 70.9% |
| LMCA | 39.3% | 20.6% |
| NYT Connections (extended) | 70.6% | — |
| Chess Puzzles | 5% | — |
| Thematic Generalization | 53% | — |
| LiveBench Reasoning | — | 44.8% |
| LiveBench Data Analysis | — | 53.7% |
| Surface Evolver Bench | 30.6% | — |
| Epoch Capabilities Index | 142.74 | — |
| LiveBench | — | 44% |
Math Gemma 4 31B IT leads
Gemma 4 31B IT: 43.2 (#81), Mistral Small: 16.4 (#293)
| Benchmark | Gemma 4 31B IT | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | 5.8% |
| LMArena Math | 1465 | 1341 |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |
Knowledge Gemma 4 31B IT leads
Gemma 4 31B IT: 37.9 (#151), Mistral Small: 31.0 (#222)
| Benchmark | Gemma 4 31B IT | Mistral Small |
|---|---|---|
| GPQA Diamond | 75.8% | 47.5% |
| Vectara Hallucination Rate | 7.4% | 5.1% |
| LMArena Expert | 1465 | 1291 |
| SimpleQA Verified | 10.4% | — |
| MMLU | — | 68.7% |
Multimodal Gemma 4 31B IT leads
Gemma 4 31B IT: 41.6 (#34), Mistral Small: 33.5 (#96)
| Benchmark | Gemma 4 31B IT | Mistral Small |
|---|---|---|
| LMArena Vision | 1277 | 1142 |
| LMArena Document | 1425 | — |
Multilingual Gemma 4 31B IT leads
Gemma 4 31B IT: 53.8 (#57), Mistral Small: 45.5 (#169)
| Benchmark | Gemma 4 31B IT | Mistral Small |
|---|---|---|
| LMArena Non-English | 1431 | 1315 |
| LMArena Chinese | 1476 | 1340 |
| LMArena French | 1435 | 1337 |
| LMArena Russian | 1460 | 1324 |
| LMArena Spanish | 1444 | 1346 |
| LMArena German | — | 1340 |
| LMArena Japanese | — | 1275 |
| LMArena Korean | — | 1259 |
Instruction Following Gemma 4 31B IT leads
Gemma 4 31B IT: 75.5 (#61), Mistral Small: 66.4 (#209)
| Benchmark | Gemma 4 31B IT | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1433 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
Long Context Gemma 4 31B IT leads
Gemma 4 31B IT: 44.2 (#71), Mistral Small: 40.4 (#156)
| Benchmark | Gemma 4 31B IT | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1446 | 1327 |
Writing & Preference Gemma 4 31B IT leads
Gemma 4 31B IT: 60.5 (#96), Mistral Small: 52.5 (#171)
| Benchmark | Gemma 4 31B IT | Mistral Small |
|---|---|---|
| LMArena Text | 1443 | 1338 |
| LMArena Creative Writing | 1415 | 1305 |
| LMArena Multi-Turn | 1452 | 1344 |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is Gemma 4 31B IT better than Mistral Small?
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 33.4 on the Noometry Index.
Which is cheaper, Gemma 4 31B IT or Mistral Small?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Mistral Small lists at $0.15 and $0.60.
Is Gemma 4 31B IT or Mistral Small better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Gemma 4 31B IT and Mistral Small share?
24 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Mistral Small has 39.