Model comparison
Gemma 4 31B IT vs Mistral 7B
Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 22.9 on the Noometry Index.
Last verified . 19 shared benchmarks.
Google
Mistral AISummary
- They share 19 benchmarks with published results for both. Gemma 4 31B IT scores higher in 8 categories and Mistral 7B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 4 31B IT leads 41.3 to 7.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 73.3% for Gemma 4 31B IT and 0.3% for Mistral 7B.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.25 / $0.25 for Mistral 7B.
- Gemma 4 31B IT accepts more context: 262K tokens versus 8K.
Side by side
| Gemma 4 31B IT | Mistral 7B | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 43.2 | 22.9 |
| Released | 2026-04-02 | 2023-09-27 |
| Weights | Open | Open |
| Context window | 262K | 8K |
| Max output | 33K | 8K |
| Input $ / M tokens | $0.09 | $0.25 |
| Output $ / M tokens | $0.34 | $0.25 |
| Results tracked | 35 | 37 |
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: 41.9 (#98), Mistral 7B: 25.9 (#321)
| Benchmark | Gemma 4 31B IT | Mistral 7B |
|---|---|---|
| LMArena Coding | 1459 | 1082 |
| LMArena WebDev | 1364 | — |
| SciCode | 43.4% | — |
| WeirdML | 52.3% | — |
| BigCodeBench Instruct | — | 19.5% |
| BigCodeBench Complete | — | 27.3% |
| ALE-Bench | 925.5 | — |
| HumanEval+ | — | 36% |
| MBPP+ | — | 42.1% |
Reasoning Gemma 4 31B IT leads
Gemma 4 31B IT: 26.4 (#119), Mistral 7B: 12.6 (#331)
| Benchmark | Gemma 4 31B IT | Mistral 7B |
|---|---|---|
| Chess Puzzles | 5% | 0% |
| LMArena Hard Prompts | 1448 | 1067 |
| DTBench | 82.7% | 42.5% |
| Epoch Capabilities Index | 142.74 | 111.97 |
| Kagi LLM Benchmark | 63.5% | — |
| NYT Connections (extended) | 70.6% | — |
| CritPt | 1.4% | — |
| Thematic Generalization | 53% | — |
| LMCA | 39.3% | — |
| Surface Evolver Bench | 30.6% | — |
| Adversarial NLI | — | 47.1% |
| BIG-Bench Hard | — | 56.1% |
| HellaSwag | — | 81% |
| PIQA | — | 83% |
| WinoGrande | — | 75.3% |
Math Gemma 4 31B IT leads
Gemma 4 31B IT: 41.3 (#72), Mistral 7B: 7.6 (#319)
| Benchmark | Gemma 4 31B IT | Mistral 7B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | 0.3% |
| LMArena Math | 1464 | 1085 |
| MATH Level 5 | — | 3.7% |
| GSM8K | — | 54.4% |
Knowledge Gemma 4 31B IT leads
Gemma 4 31B IT: 37.9 (#141), Mistral 7B: 7.3 (#306)
| Benchmark | Gemma 4 31B IT | Mistral 7B |
|---|---|---|
| GPQA Diamond | 75.8% | 15.2% |
| LMArena Expert | 1465 | 1036 |
| SimpleQA Verified | 10.4% | — |
| Vectara Hallucination Rate | 7.4% | — |
| ARC (AI2) Challenge | — | 78.6% |
| BoolQ | — | 87.4% |
| MMLU | — | 62.5% |
| OpenBookQA | — | 79.8% |
| TriviaQA | — | 75.2% |
Multimodal Not comparable
Gemma 4 31B IT: 41.0 (#32), Mistral 7B: —
| Benchmark | Gemma 4 31B IT | Mistral 7B |
|---|---|---|
| LMArena Vision | 1278 | — |
| LMArena Document | 1425 | — |
Multilingual Gemma 4 31B IT leads
Gemma 4 31B IT: 54.0 (#52), Mistral 7B: 26.0 (#278)
| Benchmark | Gemma 4 31B IT | Mistral 7B |
|---|---|---|
| LMArena Non-English | 1431 | 1012 |
| LMArena Chinese | 1478 | 1009 |
| LMArena French | 1436 | 1036 |
| LMArena Russian | 1462 | 1018 |
| LMArena Spanish | 1443 | 1026 |
| LMArena German | — | 987 |
| LMArena Japanese | — | 878 |
Instruction Following Gemma 4 31B IT leads
Gemma 4 31B IT: 75.6 (#58), Mistral 7B: 54.5 (#275)
| Benchmark | Gemma 4 31B IT | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 1433 | 1060 |
Long Context Gemma 4 31B IT leads
Gemma 4 31B IT: 44.2 (#67), Mistral 7B: 32.2 (#266)
| Benchmark | Gemma 4 31B IT | Mistral 7B |
|---|---|---|
| LMArena Longer Query | 1446 | 1060 |
Writing & Preference Gemma 4 31B IT leads
Gemma 4 31B IT: 60.7 (#92), Mistral 7B: 30.9 (#281)
| Benchmark | Gemma 4 31B IT | Mistral 7B |
|---|---|---|
| LMArena Text | 1443 | 1090 |
| LMArena Creative Writing | 1416 | 1068 |
| LMArena Multi-Turn | 1452 | 1062 |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than Mistral 7B?
Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 22.9 on the Noometry Index.
Which is cheaper, Gemma 4 31B IT or Mistral 7B?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Mistral 7B lists at $0.25 and $0.25.
Is Gemma 4 31B IT or Mistral 7B better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 41.9 versus 25.9 in the Noometry coding category.
Which has the bigger context window?
Gemma 4 31B IT does, with 262K tokens against 8K.
How many benchmarks do Gemma 4 31B IT and Mistral 7B share?
19 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Mistral 7B has 37.