Model comparison
Gemma 4 31B IT vs Mistral Medium
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 36.3 on the Noometry Index.
Last verified . 26 shared benchmarks.
Google
Mistral AISummary
- They share 26 benchmarks with published results for both. Gemma 4 31B IT scores higher in 9 categories and Mistral Medium in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 4 31B IT leads 43.2 to 28.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 73.3% for Gemma 4 31B IT and 32.2% for Mistral Medium.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
Side by side
| Gemma 4 31B IT | Mistral Medium | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 43.5 | 36.3 |
| Released | 2026-04-02 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 33K | 262K |
| Input $ / M tokens | $0.09 | $1.50 |
| Output $ / M tokens | $0.34 | $7.50 |
| Results tracked | 35 | 36 |
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 Medium: 34.2 (#243)
| Benchmark | Gemma 4 31B IT | Mistral Medium |
|---|---|---|
| SciCode | 43.4% | 40.2% |
| WeirdML | 52.3% | 43.7% |
| LMArena Coding | 1459 | 1434 |
| ALE-Bench | 925.5 | 763.98 |
| FrontierCode | — | 8% |
| LMArena WebDev | 1366 | — |
Agentic & Tool Use Not comparable
Gemma 4 31B IT: —, Mistral Medium: 28.3 (#90)
| Benchmark | Gemma 4 31B IT | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
Reasoning Gemma 4 31B IT leads
Gemma 4 31B IT: 27.2 (#122), Mistral Medium: 24.0 (#167)
| Benchmark | Gemma 4 31B IT | Mistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 63.5% | 50% |
| CritPt | 1.4% | 0% |
| LMArena Hard Prompts | 1448 | 1426 |
| DTBench | 82.7% | 75.5% |
| LMCA | 39.3% | 26.1% |
| Surface Evolver Bench | 30.6% | 26.9% |
| NYT Connections (extended) | 70.6% | — |
| Chess Puzzles | 5% | — |
| Thematic Generalization | 53% | — |
| Epoch Capabilities Index | 142.74 | — |
Math Gemma 4 31B IT leads
Gemma 4 31B IT: 43.2 (#81), Mistral Medium: 28.1 (#245)
| Benchmark | Gemma 4 31B IT | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | 32.2% |
| LMArena Math | 1465 | 1408 |
| ProofBench | — | 9% |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Gemma 4 31B IT leads
Gemma 4 31B IT: 37.9 (#151), Mistral Medium: 25.0 (#265)
| Benchmark | Gemma 4 31B IT | Mistral Medium |
|---|---|---|
| GPQA Diamond | 75.8% | 59.5% |
| Vectara Hallucination Rate | 7.4% | 22.7% |
| LMArena Expert | 1465 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| SimpleQA Verified | 10.4% | — |
Multimodal Gemma 4 31B IT leads
Gemma 4 31B IT: 41.6 (#34), Mistral Medium: 35.3 (#88)
| Benchmark | Gemma 4 31B IT | Mistral Medium |
|---|---|---|
| LMArena Vision | 1277 | 1172 |
| LMArena Document | 1425 | — |
Multilingual Gemma 4 31B IT leads
Gemma 4 31B IT: 53.8 (#57), Mistral Medium: 52.1 (#91)
| Benchmark | Gemma 4 31B IT | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1431 | 1408 |
| LMArena Chinese | 1476 | 1447 |
| LMArena French | 1435 | 1459 |
| LMArena Russian | 1460 | 1411 |
| LMArena Spanish | 1444 | 1433 |
| LMArena German | — | 1432 |
| LMArena Japanese | — | 1378 |
| LMArena Korean | — | 1380 |
Instruction Following Gemma 4 31B IT leads
Gemma 4 31B IT: 75.5 (#61), Mistral Medium: 73.7 (#116)
| Benchmark | Gemma 4 31B IT | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1433 | 1398 |
Long Context Gemma 4 31B IT leads
Gemma 4 31B IT: 44.2 (#71), Mistral Medium: 42.9 (#114)
| Benchmark | Gemma 4 31B IT | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1446 | 1406 |
Writing & Preference Too close to call
Gemma 4 31B IT: 60.5 (#96), Mistral Medium: 60.0 (#103)
| Benchmark | Gemma 4 31B IT | Mistral Medium |
|---|---|---|
| LMArena Text | 1443 | 1424 |
| LMArena Creative Writing | 1415 | 1391 |
| LMArena Multi-Turn | 1452 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than Mistral Medium?
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 36.3 on the Noometry Index.
Which is cheaper, Gemma 4 31B IT or Mistral Medium?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Gemma 4 31B IT or Mistral Medium better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 34.2 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 Medium share?
26 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Mistral Medium has 36.