Model comparison
Claude 3 Opus vs Gemma 4 31B IT
Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 29.3 on the Noometry Index.
Last verified . 23 shared benchmarks.
GoogleSummary
- They share 23 benchmarks with published results for both. Claude 3 Opus 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 13.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus 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 Opus | Gemma 4 31B IT | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 29.3 | 43.2 |
| Released | 2024-02-29 | 2026-04-02 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.09 |
| Output $ / M tokens | — | $0.34 |
| Results tracked | 46 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 31B IT leads
Claude 3 Opus: 32.4 (#261), Gemma 4 31B IT: 41.9 (#98)
| Benchmark | Claude 3 Opus | Gemma 4 31B IT |
|---|---|---|
| WeirdML | 19.2% | 52.3% |
| LMArena Coding | 1264 | 1459 |
| LMArena WebDev | — | 1364 |
| SciCode | — | 43.4% |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 925.5 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Not comparable
Claude 3 Opus: 24.3 (#110), Gemma 4 31B IT: —
| Benchmark | Claude 3 Opus | Gemma 4 31B IT |
|---|---|---|
| Cybench | 10% | — |
| METR Time Horizons | 29.5% | — |
Reasoning Gemma 4 31B IT leads
Claude 3 Opus: 14.2 (#318), Gemma 4 31B IT: 26.4 (#119)
| Benchmark | Claude 3 Opus | Gemma 4 31B IT |
|---|---|---|
| Chess Puzzles | 5% | 5% |
| LMArena Hard Prompts | 1246 | 1448 |
| DTBench | 61.6% | 82.7% |
| LMCA | 17% | 39.3% |
| Epoch Capabilities Index | 126.91 | 142.74 |
| SimpleBench | 23.5% | — |
| Kagi LLM Benchmark | — | 63.5% |
| NYT Connections (extended) | — | 70.6% |
| CritPt | — | 1.4% |
| EnigmaEval | 0.8% | — |
| Thematic Generalization | — | 53% |
| LiveBench Reasoning | 40.6% | — |
| LiveBench Data Analysis | 57.9% | — |
| Surface Evolver Bench | — | 30.6% |
| ForecastBench | 58.4 | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math Gemma 4 31B IT leads
Claude 3 Opus: 13.9 (#293), Gemma 4 31B IT: 41.3 (#72)
| Benchmark | Claude 3 Opus | Gemma 4 31B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 73.3% |
| LMArena Math | 1273 | 1464 |
| LiveBench Math | 43.6% | — |
| MATH Level 5 | 37.5% | — |
Knowledge Gemma 4 31B IT leads
Claude 3 Opus: 24.5 (#262), Gemma 4 31B IT: 37.9 (#141)
| Benchmark | Claude 3 Opus | Gemma 4 31B IT |
|---|---|---|
| GPQA Diamond | 47.2% | 75.8% |
| SimpleQA Verified | 12.6% | 10.4% |
| LMArena Expert | 1223 | 1465 |
| Confabulations | 22.7% | — |
| Vectara Hallucination Rate | — | 7.4% |
| MMLU | 84.6% | — |
Multimodal Gemma 4 31B IT leads
Claude 3 Opus: 26.6 (#112), Gemma 4 31B IT: 41.0 (#32)
| Benchmark | Claude 3 Opus | Gemma 4 31B IT |
|---|---|---|
| LMArena Vision | 1023 | 1278 |
| LMArena Document | — | 1425 |
Multilingual Gemma 4 31B IT leads
Claude 3 Opus: 41.6 (#202), Gemma 4 31B IT: 54.0 (#52)
| Benchmark | Claude 3 Opus | Gemma 4 31B IT |
|---|---|---|
| LMArena Non-English | 1258 | 1431 |
| LMArena Chinese | 1248 | 1478 |
| LMArena French | 1274 | 1436 |
| LMArena Russian | 1280 | 1462 |
| LMArena Spanish | 1246 | 1443 |
| LMArena German | 1258 | — |
| LMArena Japanese | 1204 | — |
| LMArena Korean | 1187 | — |
Instruction Following Gemma 4 31B IT leads
Claude 3 Opus: 64.3 (#223), Gemma 4 31B IT: 75.6 (#58)
| Benchmark | Claude 3 Opus | Gemma 4 31B IT |
|---|---|---|
| LMArena Instruction Following | 1248 | 1433 |
| LiveBench Instruction Following | 63.9% | — |
Long Context Gemma 4 31B IT leads
Claude 3 Opus: 38.2 (#197), Gemma 4 31B IT: 44.2 (#67)
| Benchmark | Claude 3 Opus | Gemma 4 31B IT |
|---|---|---|
| LMArena Longer Query | 1259 | 1446 |
Writing & Preference Gemma 4 31B IT leads
Claude 3 Opus: 47.4 (#208), Gemma 4 31B IT: 60.7 (#92)
| Benchmark | Claude 3 Opus | Gemma 4 31B IT |
|---|---|---|
| LMArena Text | 1262 | 1443 |
| LMArena Creative Writing | 1235 | 1416 |
| LMArena Multi-Turn | 1275 | 1452 |
| EQ-Bench Creative Writing | — | 1368 |
| EQ-Bench 4 | — | 1120 |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than Gemma 4 31B IT?
Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 29.3 on the Noometry Index.
Is Claude 3 Opus or Gemma 4 31B IT better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 41.9 versus 32.4 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and Gemma 4 31B IT share?
23 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Gemma 4 31B IT has 35.