Model comparison
Claude 3.5 Sonnet vs Gemma 4 31B IT
Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 34.4 on the Noometry Index.
Last verified . 21 shared benchmarks.
GoogleSummary
- They share 21 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 0 categories and Gemma 4 31B IT in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 4 31B IT leads 41.3 to 18.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 73.3% for Gemma 4 31B IT.
- Gemma 4 31B IT has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Sonnet | Gemma 4 31B IT | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 34.4 | 43.2 |
| Released | 2024-06-20 | 2026-04-02 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.09 |
| Output $ / M tokens | — | $0.34 |
| Results tracked | 60 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 31B IT leads
Claude 3.5 Sonnet: 39.5 (#145), Gemma 4 31B IT: 41.9 (#98)
| Benchmark | Claude 3.5 Sonnet | Gemma 4 31B IT |
|---|---|---|
| WeirdML | 40% | 52.3% |
| LMArena Coding | 1343 | 1459 |
| Aider Polyglot | 51.6% | — |
| LMArena WebDev | — | 1364 |
| SciCode | — | 43.4% |
| GSO | 4.6% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| ALE-Bench | — | 925.5 |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Not comparable
Claude 3.5 Sonnet: 32.1 (#61), Gemma 4 31B IT: —
| Benchmark | Claude 3.5 Sonnet | Gemma 4 31B IT |
|---|---|---|
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
Reasoning Gemma 4 31B IT leads
Claude 3.5 Sonnet: 22.5 (#176), Gemma 4 31B IT: 26.4 (#119)
| Benchmark | Claude 3.5 Sonnet | Gemma 4 31B IT |
|---|---|---|
| LMArena Hard Prompts | 1305 | 1448 |
| DTBench | 67.8% | 82.7% |
| Epoch Capabilities Index | 133.55 | 142.74 |
| SimpleBench | 41.4% | — |
| Kagi LLM Benchmark | — | 63.5% |
| NYT Connections (extended) | — | 70.6% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 5% |
| EnigmaEval | 0.9% | — |
| Thematic Generalization | — | 53% |
| LiveBench Reasoning | 56.7% | — |
| LiveBench Data Analysis | 55% | — |
| LMCA | — | 39.3% |
| Surface Evolver Bench | — | 30.6% |
| ForecastBench | 60.7 | — |
| LiveBench | 59% | — |
Math Gemma 4 31B IT leads
Claude 3.5 Sonnet: 18.0 (#282), Gemma 4 31B IT: 41.3 (#72)
| Benchmark | Claude 3.5 Sonnet | Gemma 4 31B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 73.3% |
| LMArena Math | 1306 | 1464 |
| Omni-MATH | 27.6% | — |
| LiveBench Math | 52.3% | — |
| MATH Level 5 | 56.9% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Gemma 4 31B IT leads
Claude 3.5 Sonnet: 28.5 (#236), Gemma 4 31B IT: 37.9 (#141)
| Benchmark | Claude 3.5 Sonnet | Gemma 4 31B IT |
|---|---|---|
| GPQA Diamond | 55.3% | 75.8% |
| LMArena Expert | 1264 | 1465 |
| Humanity's Last Exam | 4.1% | — |
| SimpleQA Verified | — | 10.4% |
| MMLU-Pro | 77.7% | — |
| Confabulations | 19.9% | — |
| Vectara Hallucination Rate | — | 7.4% |
| GPQA (HELM) | 56.5% | — |
| MMLU | 87.3% | — |
Multimodal Gemma 4 31B IT leads
Claude 3.5 Sonnet: 26.0 (#115), Gemma 4 31B IT: 41.0 (#32)
| Benchmark | Claude 3.5 Sonnet | Gemma 4 31B IT |
|---|---|---|
| LMArena Vision | 1125 | 1278 |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
| LMArena Document | — | 1425 |
Multilingual Gemma 4 31B IT leads
Claude 3.5 Sonnet: 43.4 (#180), Gemma 4 31B IT: 54.0 (#52)
| Benchmark | Claude 3.5 Sonnet | Gemma 4 31B IT |
|---|---|---|
| LMArena Non-English | 1283 | 1431 |
| LMArena Chinese | 1271 | 1478 |
| LMArena French | 1304 | 1436 |
| LMArena Russian | 1305 | 1462 |
| LMArena Spanish | 1289 | 1443 |
| LMArena German | 1297 | — |
| LMArena Japanese | 1234 | — |
| LMArena Korean | 1200 | — |
Instruction Following Gemma 4 31B IT leads
Claude 3.5 Sonnet: 69.0 (#177), Gemma 4 31B IT: 75.6 (#58)
| Benchmark | Claude 3.5 Sonnet | Gemma 4 31B IT |
|---|---|---|
| LMArena Instruction Following | 1297 | 1433 |
| LiveBench Instruction Following | 69.3% | — |
| IFEval | 85.5% | — |
Long Context Gemma 4 31B IT leads
Claude 3.5 Sonnet: 39.9 (#162), Gemma 4 31B IT: 44.2 (#67)
| Benchmark | Claude 3.5 Sonnet | Gemma 4 31B IT |
|---|---|---|
| LMArena Longer Query | 1311 | 1446 |
Writing & Preference Gemma 4 31B IT leads
Claude 3.5 Sonnet: 53.0 (#159), Gemma 4 31B IT: 60.7 (#92)
| Benchmark | Claude 3.5 Sonnet | Gemma 4 31B IT |
|---|---|---|
| LMArena Text | 1298 | 1443 |
| LMArena Creative Writing | 1292 | 1416 |
| EQ-Bench Creative Writing | 1451 | 1368 |
| LMArena Multi-Turn | 1326 | 1452 |
| Short-Story Creative Writing | 80.3% | — |
| WildBench | 79.2% | — |
| EQ-Bench 4 | — | 1120 |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Gemma 4 31B IT?
Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 34.4 on the Noometry Index.
Is Claude 3.5 Sonnet or Gemma 4 31B IT better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 41.9 versus 39.5 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Gemma 4 31B IT share?
21 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Gemma 4 31B IT has 35.