# Claude Opus 5.5 vs Gemma 4 31B IT

> Claude Opus 5.5 is the stronger model overall, scoring 68.5 to 43.2 on the Noometry Index. Gemma 4 31B IT costs 52× less per token, which makes it the better buy when Claude Opus 5.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-opus-5-5-vs-gemma-4-31b-it
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Claude Opus 5.5 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 5.5 leads 79.5 to 26.4.
- The biggest single-benchmark swing is SimpleQA Verified: 72.2% for Claude Opus 5.5 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 $4 / $20 for Claude Opus 5.5.
- Claude Opus 5.5 accepts more context: 1M tokens versus 262K.
- Gemma 4 31B IT has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Opus 5.5 | Gemma 4 31B IT |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 68.5 | 43.2 |
| Rank | 3 | 85 |
| Context | 1M | 262K |
| Input $/M | $4 | $0.09 |
| Output $/M | $20 | $0.34 |
| Weights | Proprietary | Open |

## Coding

- Claude Opus 5.5: 71.4 (#1)
- Gemma 4 31B IT: 41.9 (#98)

| Benchmark | Claude Opus 5.5 | Gemma 4 31B IT |
|---|---|---|
| LMArena WebDev | 1820 | 1364 |
| SciCode | 66.9% | 43.4% |
| LMArena Coding | 1545 | 1459 |
| FrontierCode | 54.4% | — |
| CursorBench | 57.8% | — |
| FrontierSWE | 62.3% | — |
| WeirdML | — | 52.3% |
| MirrorCode | 77.4% | — |
| ALE-Bench | — | 925.5 |

## Agentic & Tool Use

- Claude Opus 5.5: 45.3 (#13)
- Gemma 4 31B IT: —

| Benchmark | Claude Opus 5.5 | Gemma 4 31B IT |
|---|---|---|
| APEX-Agents | 73.5% | — |
| GDP.pdf | 30.6% | — |

## Reasoning

- Claude Opus 5.5: 79.5 (#2)
- Gemma 4 31B IT: 26.4 (#119)

| Benchmark | Claude Opus 5.5 | Gemma 4 31B IT |
|---|---|---|
| NYT Connections (extended) | 88.5% | 70.6% |
| CritPt | 31.7% | 1.4% |
| LMArena Hard Prompts | 1545 | 1448 |
| DTBench | 98.9% | 82.7% |
| LMCA | 68.2% | 39.3% |
| ARC-AGI-2 | 92.5% | — |
| Kagi LLM Benchmark | — | 63.5% |
| ARC-AGI-1 | 97.5% | — |
| Chess Puzzles | — | 5% |
| Thematic Generalization | — | 53% |
| EBR-Bench | 71.4% | — |
| Mystery Game Puzzles | 71% | — |
| Surface Evolver Bench | — | 30.6% |
| Epoch Capabilities Index | — | 142.74 |

## Math

- Claude Opus 5.5: 92.4 (#2)
- Gemma 4 31B IT: 41.3 (#72)

| Benchmark | Claude Opus 5.5 | Gemma 4 31B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 73.3% |
| FrontierMath (Tiers 1-3) | 91.2% | — |
| FrontierMath Tier 4 | 95% | — |
| ProofBench | 100% | — |
| LMArena Math | — | 1464 |

## Knowledge

- Claude Opus 5.5: 66.6 (#9)
- Gemma 4 31B IT: 37.9 (#141)

| Benchmark | Claude Opus 5.5 | Gemma 4 31B IT |
|---|---|---|
| GPQA Diamond | 90.6% | 75.8% |
| SimpleQA Verified | 72.2% | 10.4% |
| LMArena Expert | 1564 | 1465 |
| Vectara Hallucination Rate | — | 7.4% |

## Multimodal

- Claude Opus 5.5: 56.5 (#2)
- Gemma 4 31B IT: 41.0 (#32)

| Benchmark | Claude Opus 5.5 | Gemma 4 31B IT |
|---|---|---|
| LMArena Vision | — | 1278 |
| Furniture Assembly | 83.3% | — |
| LMArena Document | — | 1425 |

## Multilingual

- Claude Opus 5.5: 59.8 (#1)
- Gemma 4 31B IT: 54.0 (#52)

| Benchmark | Claude Opus 5.5 | Gemma 4 31B IT |
|---|---|---|
| LMArena Non-English | 1513 | 1431 |
| LMArena Chinese | 1572 | 1478 |
| LMArena Russian | 1532 | 1462 |
| LMArena French | — | 1436 |
| LMArena Spanish | — | 1443 |

## Instruction Following

- Claude Opus 5.5: 80.1 (#2)
- Gemma 4 31B IT: 75.6 (#58)

| Benchmark | Claude Opus 5.5 | Gemma 4 31B IT |
|---|---|---|
| LMArena Instruction Following | 1535 | 1433 |

## Long Context

- Claude Opus 5.5: 47.3 (#18)
- Gemma 4 31B IT: 44.2 (#67)

| Benchmark | Claude Opus 5.5 | Gemma 4 31B IT |
|---|---|---|
| LMArena Longer Query | 1540 | 1446 |

## Writing & Preference

- Claude Opus 5.5: 78.7 (#3)
- Gemma 4 31B IT: 60.7 (#92)

| Benchmark | Claude Opus 5.5 | Gemma 4 31B IT |
|---|---|---|
| LMArena Text | 1518 | 1443 |
| LMArena Creative Writing | 1538 | 1416 |
| EQ-Bench Creative Writing | 2050 | 1368 |
| LMArena Multi-Turn | 1520 | 1452 |
| EQ-Bench 4 | — | 1120 |

## FAQ

### Is Claude Opus 5.5 better than Gemma 4 31B IT?

Claude Opus 5.5 is the stronger model overall, scoring 68.5 to 43.2 on the Noometry Index. Gemma 4 31B IT costs 52× less per token, which makes it the better buy when Claude Opus 5.5's lead doesn't matter for your workload.

### Which is cheaper, Claude Opus 5.5 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 5.5 lists at $4 and $20.

### Is Claude Opus 5.5 or Gemma 4 31B IT better for coding?

Claude Opus 5.5 scores higher on coding benchmarks: 71.4 versus 41.9 in the Noometry coding category.

### Which has the bigger context window?

Claude Opus 5.5 does, with 1M tokens against 262K.

### How many benchmarks do Claude Opus 5.5 and Gemma 4 31B IT share?

21 benchmarks have published results for both models. Claude Opus 5.5 has 35 scored results on Noometry and Gemma 4 31B IT has 35.