Model comparison
Claude Opus 4.1 vs Gemma 4 31B IT
Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 40.8 on the Noometry Index.
Last verified . 24 shared benchmarks.
GoogleSummary
- They share 24 benchmarks with published results for both. Claude Opus 4.1 scores higher in 6 categories and Gemma 4 31B IT in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 4 31B IT leads 41.3 to 22.0.
- The biggest single-benchmark swing is WeirdML: 45.9% for Claude Opus 4.1 and 52.3% for Gemma 4 31B IT.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $15 / $75 for Claude Opus 4.1.
- Gemma 4 31B IT accepts more context: 262K tokens versus 200K.
- Gemma 4 31B IT has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4.1 | Gemma 4 31B IT | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 40.8 | 43.2 |
| Released | 2025-08-05 | 2026-04-02 |
| Weights | Proprietary | Open |
| Context window | 200K | 262K |
| Max output | 32K | 33K |
| Input $ / M tokens | $15 | $0.09 |
| Output $ / M tokens | $75 | $0.34 |
| Results tracked | 48 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.1 leads
Claude Opus 4.1: 44.3 (#69), Gemma 4 31B IT: 41.9 (#98)
| Benchmark | Claude Opus 4.1 | Gemma 4 31B IT |
|---|---|---|
| LMArena WebDev | 1390 | 1364 |
| WeirdML | 45.9% | 52.3% |
| LMArena Coding | 1479 | 1459 |
| ALE-Bench | 674.77 | 925.5 |
| SWE-bench Verified | 73.3% | — |
| SciCode | — | 43.4% |
| AlgoTune | 1.34 | — |
Agentic & Tool Use Not comparable
Claude Opus 4.1: 34.8 (#38), Gemma 4 31B IT: —
| Benchmark | Claude Opus 4.1 | Gemma 4 31B IT |
|---|---|---|
| Terminal-Bench | 38% | — |
| GDPval | 43.6% | — |
| Cybench | 42% | — |
| DeepResearch Bench | 48.3% | — |
| LMArena Search | 1148 | — |
| METR Time Horizons | 66.8% | — |
Reasoning Claude Opus 4.1 leads
Claude Opus 4.1: 31.6 (#70), Gemma 4 31B IT: 26.4 (#119)
| Benchmark | Claude Opus 4.1 | Gemma 4 31B IT |
|---|---|---|
| Chess Puzzles | 7% | 5% |
| LMArena Hard Prompts | 1443 | 1448 |
| DTBench | 80% | 82.7% |
| LMCA | 37.1% | 39.3% |
| Epoch Capabilities Index | 144.11 | 142.74 |
| SimpleBench | 60% | — |
| Kagi LLM Benchmark | — | 63.5% |
| NYT Connections (extended) | — | 70.6% |
| CritPt | — | 1.4% |
| EnigmaEval | 7.2% | — |
| Thematic Generalization | — | 53% |
| EBR-Bench | 7.9% | — |
| Mystery Game Puzzles | 21% | — |
| Surface Evolver Bench | — | 30.6% |
| ForecastBench | 62 | — |
Math Gemma 4 31B IT leads
Claude Opus 4.1: 22.0 (#267), Gemma 4 31B IT: 41.3 (#72)
| Benchmark | Claude Opus 4.1 | Gemma 4 31B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 68.9% | 73.3% |
| LMArena Math | 1430 | 1464 |
| FrontierMath (Tiers 1-3) | 12.6% | — |
| FrontierMath Tier 4 | 2.4% | — |
| FrontierMath (Feb 2025 set) | 7.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Opus 4.1 leads
Claude Opus 4.1: 41.9 (#93), Gemma 4 31B IT: 37.9 (#141)
| Benchmark | Claude Opus 4.1 | Gemma 4 31B IT |
|---|---|---|
| GPQA Diamond | 77.3% | 75.8% |
| Vectara Hallucination Rate | 11.8% | 7.4% |
| LMArena Expert | 1439 | 1465 |
| Humanity's Last Exam | 11.5% | — |
| SimpleQA Verified | — | 10.4% |
| Confabulations | 17.1% | — |
Multimodal Gemma 4 31B IT leads
Claude Opus 4.1: 26.2 (#114), Gemma 4 31B IT: 41.0 (#32)
| Benchmark | Claude Opus 4.1 | Gemma 4 31B IT |
|---|---|---|
| LMArena Vision | — | 1278 |
| VPCT | 35% | — |
| LMArena Document | — | 1425 |
Multilingual Gemma 4 31B IT leads
Claude Opus 4.1: 52.1 (#90), Gemma 4 31B IT: 54.0 (#52)
| Benchmark | Claude Opus 4.1 | Gemma 4 31B IT |
|---|---|---|
| LMArena Non-English | 1405 | 1431 |
| LMArena Chinese | 1427 | 1478 |
| LMArena French | 1432 | 1436 |
| LMArena Russian | 1421 | 1462 |
| LMArena Spanish | 1448 | 1443 |
| LMArena German | 1412 | — |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1381 | — |
Instruction Following Too close to call
Claude Opus 4.1: 75.8 (#53), Gemma 4 31B IT: 75.6 (#58)
| Benchmark | Claude Opus 4.1 | Gemma 4 31B IT |
|---|---|---|
| LMArena Instruction Following | 1436 | 1433 |
Long Context Too close to call
Claude Opus 4.1: 44.5 (#60), Gemma 4 31B IT: 44.2 (#67)
| Benchmark | Claude Opus 4.1 | Gemma 4 31B IT |
|---|---|---|
| LMArena Longer Query | 1455 | 1446 |
Writing & Preference Claude Opus 4.1 leads
Claude Opus 4.1: 62.6 (#70), Gemma 4 31B IT: 60.7 (#92)
| Benchmark | Claude Opus 4.1 | Gemma 4 31B IT |
|---|---|---|
| LMArena Text | 1419 | 1443 |
| LMArena Creative Writing | 1412 | 1416 |
| LMArena Multi-Turn | 1444 | 1452 |
| Short-Story Creative Writing | 84.7% | — |
| EQ-Bench Creative Writing | — | 1368 |
| EQ-Bench 4 | — | 1120 |
Frequently asked questions
Is Claude Opus 4.1 better than Gemma 4 31B IT?
Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 40.8 on the Noometry Index.
Which is cheaper, Claude Opus 4.1 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; Claude Opus 4.1 lists at $15 and $75.
Is Claude Opus 4.1 or Gemma 4 31B IT better for coding?
Claude Opus 4.1 scores higher on coding benchmarks: 44.3 versus 41.9 in the Noometry coding category.
Which has the bigger context window?
Gemma 4 31B IT does, with 262K tokens against 200K.
How many benchmarks do Claude Opus 4.1 and Gemma 4 31B IT share?
24 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and Gemma 4 31B IT has 35.