Model comparison
Codestral vs Gemma 4 31B IT
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 30.6 on the Noometry Index.
Last verified . 2 shared benchmarks.
Mistral AI
GoogleSummary
- They share 2 benchmarks with published results for both. Codestral scores higher in 0 categories and Gemma 4 31B IT in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where Gemma 4 31B IT leads 42.3 to 27.3.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 32.5% for Codestral and 63.5% for Gemma 4 31B IT.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.30 / $0.90 for Codestral.
- Gemma 4 31B IT accepts more context: 262K tokens versus 256K.
- Gemma 4 31B IT has downloadable open weights; the other is API-only.
Side by side
| Codestral | Gemma 4 31B IT | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 30.6 | 43.5 |
| Released | 2024-05-29 | 2026-04-02 |
| Weights | Proprietary | Open |
| Context window | 256K | 262K |
| Max output | 8K | 33K |
| Input $ / M tokens | $0.30 | $0.09 |
| Output $ / M tokens | $0.90 | $0.34 |
| Results tracked | 7 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 31B IT leads
Codestral: 27.3 (#321), Gemma 4 31B IT: 42.3 (#108)
| Benchmark | Codestral | Gemma 4 31B IT |
|---|---|---|
| ALE-Bench | 137.78 | 925.5 |
| Aider Polyglot | 11.1% | — |
| LMArena WebDev | — | 1366 |
| SciCode | — | 43.4% |
| WeirdML | — | 52.3% |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1459 |
| BigCodeBench Complete | 52.5% | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Gemma 4 31B IT leads
Codestral: 19.8 (#251), Gemma 4 31B IT: 27.2 (#122)
| Benchmark | Codestral | Gemma 4 31B IT |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | 63.5% |
| NYT Connections (extended) | — | 70.6% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 5% |
| Thematic Generalization | — | 53% |
| LMArena Hard Prompts | — | 1448 |
| DTBench | — | 82.7% |
| LMCA | — | 39.3% |
| Surface Evolver Bench | — | 30.6% |
| Epoch Capabilities Index | — | 142.74 |
Math Not comparable
Codestral: —, Gemma 4 31B IT: 43.2 (#81)
| Benchmark | Codestral | Gemma 4 31B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 73.3% |
| LMArena Math | — | 1465 |
Knowledge Not comparable
Codestral: —, Gemma 4 31B IT: 37.9 (#151)
| Benchmark | Codestral | Gemma 4 31B IT |
|---|---|---|
| GPQA Diamond | — | 75.8% |
| SimpleQA Verified | — | 10.4% |
| Vectara Hallucination Rate | — | 7.4% |
| LMArena Expert | — | 1465 |
Multimodal Not comparable
Codestral: —, Gemma 4 31B IT: 41.6 (#34)
| Benchmark | Codestral | Gemma 4 31B IT |
|---|---|---|
| LMArena Vision | — | 1277 |
| LMArena Document | — | 1425 |
Multilingual Not comparable
Codestral: —, Gemma 4 31B IT: 53.8 (#57)
| Benchmark | Codestral | Gemma 4 31B IT |
|---|---|---|
| LMArena Non-English | — | 1431 |
| LMArena Chinese | — | 1476 |
| LMArena French | — | 1435 |
| LMArena Russian | — | 1460 |
| LMArena Spanish | — | 1444 |
Instruction Following Not comparable
Codestral: —, Gemma 4 31B IT: 75.5 (#61)
| Benchmark | Codestral | Gemma 4 31B IT |
|---|---|---|
| LMArena Instruction Following | — | 1433 |
Long Context Not comparable
Codestral: —, Gemma 4 31B IT: 44.2 (#71)
| Benchmark | Codestral | Gemma 4 31B IT |
|---|---|---|
| LMArena Longer Query | — | 1446 |
Writing & Preference Not comparable
Codestral: —, Gemma 4 31B IT: 60.5 (#96)
| Benchmark | Codestral | Gemma 4 31B IT |
|---|---|---|
| LMArena Text | — | 1443 |
| LMArena Creative Writing | — | 1415 |
| EQ-Bench Creative Writing | — | 1368 |
| EQ-Bench 4 | — | 1120 |
| LMArena Multi-Turn | — | 1452 |
Frequently asked questions
Is Codestral better than Gemma 4 31B IT?
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 30.6 on the Noometry Index.
Which is cheaper, Codestral or Gemma 4 31B IT?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Codestral lists at $0.30 and $0.90.
Is Codestral or Gemma 4 31B IT better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 27.3 in the Noometry coding category.
Which has the bigger context window?
Gemma 4 31B IT does, with 262K tokens against 256K.
How many benchmarks do Codestral and Gemma 4 31B IT share?
2 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Gemma 4 31B IT has 35.