Model comparison
Claude Sonnet 5 vs Gemma 4 31B IT
Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 43.2 on the Noometry Index. Gemma 4 31B IT costs 26× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Last verified . 32 shared benchmarks.
GoogleSummary
- They share 32 benchmarks with published results for both. Claude Sonnet 5 scores higher in 8 categories and Gemma 4 31B IT in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.1 to 41.3.
- The biggest single-benchmark swing is Chess Puzzles: 35% for Claude Sonnet 5 and 5% for Gemma 4 31B IT.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
- Claude Sonnet 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 Sonnet 5 | Gemma 4 31B IT | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 54.5 | 43.2 |
| Released | 2026-06-29 | 2026-04-02 |
| Weights | Proprietary | Open |
| Context window | 1M | 262K |
| Max output | 128K | 33K |
| Input $ / M tokens | $2 | $0.09 |
| Output $ / M tokens | $10 | $0.34 |
| Results tracked | 51 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5 leads
Claude Sonnet 5: 55.5 (#20), Gemma 4 31B IT: 41.9 (#98)
| Benchmark | Claude Sonnet 5 | Gemma 4 31B IT |
|---|---|---|
| LMArena WebDev | 1540 | 1364 |
| SciCode | 53.6% | 43.4% |
| WeirdML | 68.8% | 52.3% |
| LMArena Coding | 1483 | 1459 |
| ALE-Bench | 1,463 | 925.5 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| CursorBench | 34.1% | — |
| GSO | 37.3% | — |
Agentic & Tool Use Not comparable
Claude Sonnet 5: 42.7 (#16), Gemma 4 31B IT: —
| Benchmark | Claude Sonnet 5 | Gemma 4 31B IT |
|---|---|---|
| APEX-Agents | 54.5% | — |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
| Vending-Bench 2 | 6,378 | — |
Reasoning Claude Sonnet 5 leads
Claude Sonnet 5: 48.2 (#37), Gemma 4 31B IT: 26.4 (#119)
| Benchmark | Claude Sonnet 5 | Gemma 4 31B IT |
|---|---|---|
| NYT Connections (extended) | 75.1% | 70.6% |
| CritPt | 16.9% | 1.4% |
| Chess Puzzles | 35% | 5% |
| LMArena Hard Prompts | 1461 | 1448 |
| DTBench | 92.5% | 82.7% |
| LMCA | 50% | 39.3% |
| Surface Evolver Bench | 60% | 30.6% |
| Epoch Capabilities Index | 156.34 | 142.74 |
| SimpleBench | 60.6% | — |
| Kagi LLM Benchmark | — | 63.5% |
| Thematic Generalization | — | 53% |
| Mystery Game Puzzles | 35% | — |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 61.1 | — |
Math Claude Sonnet 5 leads
Claude Sonnet 5: 66.1 (#21), Gemma 4 31B IT: 41.3 (#72)
| Benchmark | Claude Sonnet 5 | Gemma 4 31B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.7% | 73.3% |
| LMArena Math | 1467 | 1464 |
| FrontierMath (Tiers 1-3) | 65.6% | — |
| FrontierMath Tier 4 | 29.3% | — |
| ProofBench | 77% | — |
Knowledge Claude Sonnet 5 leads
Claude Sonnet 5: 55.7 (#42), Gemma 4 31B IT: 37.9 (#141)
| Benchmark | Claude Sonnet 5 | Gemma 4 31B IT |
|---|---|---|
| GPQA Diamond | 90.5% | 75.8% |
| SimpleQA Verified | 33.7% | 10.4% |
| LMArena Expert | 1491 | 1465 |
| Vectara Hallucination Rate | — | 7.4% |
Multimodal Claude Sonnet 5 leads
Claude Sonnet 5: 42.4 (#26), Gemma 4 31B IT: 41.0 (#32)
| Benchmark | Claude Sonnet 5 | Gemma 4 31B IT |
|---|---|---|
| LMArena Vision | 1275 | 1278 |
| LMArena Document | 1466 | 1425 |
| Blueprint-Bench 2 | 24.9% | — |
Multilingual Too close to call
Claude Sonnet 5: 54.0 (#55), Gemma 4 31B IT: 54.0 (#52)
| Benchmark | Claude Sonnet 5 | Gemma 4 31B IT |
|---|---|---|
| LMArena Non-English | 1431 | 1431 |
| LMArena Chinese | 1475 | 1478 |
| LMArena French | 1457 | 1436 |
| LMArena Russian | 1452 | 1462 |
| LMArena Spanish | 1436 | 1443 |
| LMArena German | 1448 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1411 | — |
Instruction Following Too close to call
Claude Sonnet 5: 76.6 (#39), Gemma 4 31B IT: 75.6 (#58)
| Benchmark | Claude Sonnet 5 | Gemma 4 31B IT |
|---|---|---|
| LMArena Instruction Following | 1453 | 1433 |
Long Context Too close to call
Claude Sonnet 5: 44.8 (#53), Gemma 4 31B IT: 44.2 (#67)
| Benchmark | Claude Sonnet 5 | Gemma 4 31B IT |
|---|---|---|
| LMArena Longer Query | 1464 | 1446 |
Writing & Preference Claude Sonnet 5 leads
Claude Sonnet 5: 69.4 (#24), Gemma 4 31B IT: 60.7 (#92)
| Benchmark | Claude Sonnet 5 | Gemma 4 31B IT |
|---|---|---|
| LMArena Text | 1443 | 1443 |
| LMArena Creative Writing | 1416 | 1416 |
| EQ-Bench Creative Writing | 1794 | 1368 |
| EQ-Bench 4 | 1236 | 1120 |
| LMArena Multi-Turn | 1454 | 1452 |
Frequently asked questions
Is Claude Sonnet 5 better than Gemma 4 31B IT?
Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 43.2 on the Noometry Index. Gemma 4 31B IT costs 26× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 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 Sonnet 5 lists at $2 and $10.
Is Claude Sonnet 5 or Gemma 4 31B IT better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 41.9 in the Noometry coding category.
Which has the bigger context window?
Claude Sonnet 5 does, with 1M tokens against 262K.
How many benchmarks do Claude Sonnet 5 and Gemma 4 31B IT share?
32 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and Gemma 4 31B IT has 35.