Model comparison
Claude Opus 5 vs Gemma 4 31B IT
Claude Opus 5 is the stronger model overall, scoring 67.8 to 43.5 on the Noometry Index. Gemma 4 31B IT costs 66× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.
Last verified . 31 shared benchmarks.
GoogleSummary
- They share 31 benchmarks with published results for both. Claude Opus 5 scores higher in 9 categories and Gemma 4 31B IT in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 5 leads 77.2 to 27.2.
- The biggest single-benchmark swing is SimpleQA Verified: 59.9% for Claude Opus 5 and 10.4% for Gemma 4 31B IT.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $5 / $25 for Claude Opus 5.
- Claude Opus 5 accepts more context: 1M tokens versus 262K.
- Gemma 4 31B IT has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 5 | Gemma 4 31B IT | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 67.8 | 43.5 |
| Released | 2026-07-24 | 2026-04-02 |
| Weights | Proprietary | Open |
| Context window | 1M | 262K |
| Max output | 128K | 33K |
| Input $ / M tokens | $5 | $0.09 |
| Output $ / M tokens | $25 | $0.34 |
| Results tracked | 57 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 5 leads
Claude Opus 5: 67.5 (#5), Gemma 4 31B IT: 42.3 (#108)
| Benchmark | Claude Opus 5 | Gemma 4 31B IT |
|---|---|---|
| LMArena WebDev | 1691 | 1366 |
| SciCode | 56.4% | 43.4% |
| WeirdML | 91.8% | 52.3% |
| LMArena Coding | 1534 | 1459 |
| ALE-Bench | 2,165 | 925.5 |
| DeepSWE | 73.6% | — |
| FrontierCode | 53.4% | — |
| CursorBench | 46.6% | — |
| FrontierSWE | 52% | — |
Agentic & Tool Use Not comparable
Claude Opus 5: 55.6 (#1), Gemma 4 31B IT: —
| Benchmark | Claude Opus 5 | Gemma 4 31B IT |
|---|---|---|
| APEX-Agents | 65.8% | — |
| OSWorld 2.0 | 31.4% | — |
| τ²-bench Banking | 48.7% | — |
| PostTrainBench | 35% | — |
| BALROG | 63.4% | — |
| GBAEval | 79.6% | — |
| GDP.pdf | 24% | — |
| Vending-Bench 2 | 11,182 | — |
Reasoning Claude Opus 5 leads
Claude Opus 5: 77.2 (#4), Gemma 4 31B IT: 27.2 (#122)
| Benchmark | Claude Opus 5 | Gemma 4 31B IT |
|---|---|---|
| NYT Connections (extended) | 94.3% | 70.6% |
| CritPt | 29.1% | 1.4% |
| Chess Puzzles | 42% | 5% |
| LMArena Hard Prompts | 1526 | 1448 |
| DTBench | 97.9% | 82.7% |
| LMCA | 64.5% | 39.3% |
| Epoch Capabilities Index | 162.78 | 142.74 |
| ARC-AGI-2 | 90.4% | — |
| SimpleBench | 80.6% | — |
| Kagi LLM Benchmark | — | 63.5% |
| ARC-AGI-1 | 97.5% | — |
| Thematic Generalization | — | 53% |
| EBR-Bench | 45.7% | — |
| Mystery Game Puzzles | 59% | — |
| Surface Evolver Bench | — | 30.6% |
| Bench to the Future 3 | 0.12 | — |
Math Claude Opus 5 leads
Claude Opus 5: 86.2 (#8), Gemma 4 31B IT: 43.2 (#81)
| Benchmark | Claude Opus 5 | Gemma 4 31B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.9% | 73.3% |
| LMArena Math | 1531 | 1465 |
| FrontierMath (Tiers 1-3) | 85.6% | — |
| FrontierMath Tier 4 | 73.2% | — |
| ProofBench | 99% | — |
Knowledge Claude Opus 5 leads
Claude Opus 5: 66.8 (#9), Gemma 4 31B IT: 37.9 (#151)
| Benchmark | Claude Opus 5 | Gemma 4 31B IT |
|---|---|---|
| GPQA Diamond | 93.9% | 75.8% |
| SimpleQA Verified | 59.9% | 10.4% |
| LMArena Expert | 1557 | 1465 |
| Vectara Hallucination Rate | — | 7.4% |
Multimodal Claude Opus 5 leads
Claude Opus 5: 50.8 (#8), Gemma 4 31B IT: 41.6 (#34)
| Benchmark | Claude Opus 5 | Gemma 4 31B IT |
|---|---|---|
| LMArena Vision | 1319 | 1277 |
| LMArena Document | 1516 | 1425 |
| Blueprint-Bench 2 | 30.4% | — |
| Furniture Assembly | 60.8% | — |
Multilingual Claude Opus 5 leads
Claude Opus 5: 58.8 (#4), Gemma 4 31B IT: 53.8 (#57)
| Benchmark | Claude Opus 5 | Gemma 4 31B IT |
|---|---|---|
| LMArena Non-English | 1501 | 1431 |
| LMArena Chinese | 1574 | 1476 |
| LMArena French | 1519 | 1435 |
| LMArena Russian | 1507 | 1460 |
| LMArena Spanish | 1519 | 1444 |
| LMArena German | 1524 | — |
| LMArena Japanese | 1516 | — |
| LMArena Korean | 1521 | — |
Instruction Following Claude Opus 5 leads
Claude Opus 5: 79.2 (#7), Gemma 4 31B IT: 75.5 (#61)
| Benchmark | Claude Opus 5 | Gemma 4 31B IT |
|---|---|---|
| LMArena Instruction Following | 1517 | 1433 |
Long Context Claude Opus 5 leads
Claude Opus 5: 46.5 (#21), Gemma 4 31B IT: 44.2 (#71)
| Benchmark | Claude Opus 5 | Gemma 4 31B IT |
|---|---|---|
| LMArena Longer Query | 1515 | 1446 |
Writing & Preference Claude Opus 5 leads
Claude Opus 5: 79.2 (#1), Gemma 4 31B IT: 60.5 (#96)
| Benchmark | Claude Opus 5 | Gemma 4 31B IT |
|---|---|---|
| LMArena Text | 1507 | 1443 |
| LMArena Creative Writing | 1491 | 1415 |
| EQ-Bench Creative Writing | 2133 | 1368 |
| EQ-Bench 4 | 1385 | 1120 |
| LMArena Multi-Turn | 1499 | 1452 |
Frequently asked questions
Is Claude Opus 5 better than Gemma 4 31B IT?
Claude Opus 5 is the stronger model overall, scoring 67.8 to 43.5 on the Noometry Index. Gemma 4 31B IT costs 66× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 5 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 5 lists at $5 and $25.
Is Claude Opus 5 or Gemma 4 31B IT better for coding?
Claude Opus 5 scores higher on coding benchmarks: 67.5 versus 42.3 in the Noometry coding category.
Which has the bigger context window?
Claude Opus 5 does, with 1M tokens against 262K.
How many benchmarks do Claude Opus 5 and Gemma 4 31B IT share?
31 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and Gemma 4 31B IT has 35.