Model comparison
Claude Opus 4.8 vs Gemma 4 31B IT
Claude Opus 4.8 is the stronger model overall, scoring 60.7 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 4.8's lead doesn't matter for your workload.
Last verified . 33 shared benchmarks.
GoogleSummary
- They share 33 benchmarks with published results for both. Claude Opus 4.8 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 4.8 leads 64.7 to 27.2.
- The biggest single-benchmark swing is Surface Evolver Bench: 87.5% for Claude Opus 4.8 and 30.6% 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 4.8.
- Claude Opus 4.8 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 4.8 | Gemma 4 31B IT | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 60.7 | 43.5 |
| Released | 2026-05-28 | 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 | 65 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.8 leads
Claude Opus 4.8: 59.9 (#12), Gemma 4 31B IT: 42.3 (#108)
| Benchmark | Claude Opus 4.8 | Gemma 4 31B IT |
|---|---|---|
| LMArena WebDev | 1556 | 1366 |
| SciCode | 53.5% | 43.4% |
| WeirdML | 82.9% | 52.3% |
| LMArena Coding | 1490 | 1459 |
| ALE-Bench | 1,564 | 925.5 |
| DeepSWE | 59% | — |
| FrontierCode | 46.5% | — |
| GSO | 47.1% | — |
Agentic & Tool Use Not comparable
Claude Opus 4.8: 47.6 (#11), Gemma 4 31B IT: —
| Benchmark | Claude Opus 4.8 | Gemma 4 31B IT |
|---|---|---|
| APEX-Agents | 48.9% | — |
| OSWorld 2.0 | 20.6% | — |
| Remote Labor Index | 8.3% | — |
| τ²-bench Banking | 39.7% | — |
| DeepResearch Bench | 50.2% | — |
| PostTrainBench | 33.8% | — |
| GBAEval | 70.9% | — |
| GDP.pdf | 24% | — |
| LMArena Search | 1204 | — |
| Vending-Bench 2 | 5,787 | — |
Reasoning Claude Opus 4.8 leads
Claude Opus 4.8: 64.7 (#16), Gemma 4 31B IT: 27.2 (#122)
| Benchmark | Claude Opus 4.8 | Gemma 4 31B IT |
|---|---|---|
| Kagi LLM Benchmark | 88.8% | 63.5% |
| NYT Connections (extended) | 91.1% | 70.6% |
| CritPt | 20.9% | 1.4% |
| Chess Puzzles | 34% | 5% |
| LMArena Hard Prompts | 1482 | 1448 |
| DTBench | 94.9% | 82.7% |
| LMCA | 57.5% | 39.3% |
| Surface Evolver Bench | 87.5% | 30.6% |
| Epoch Capabilities Index | 158.21 | 142.74 |
| ARC-AGI-2 | 72.1% | — |
| SimpleBench | 64.8% | — |
| ARC-AGI-1 | 92.5% | — |
| EnigmaEval | 23.5% | — |
| Thematic Generalization | — | 53% |
| EBR-Bench | 28.6% | — |
| Mystery Game Puzzles | 36% | — |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 59.9 | — |
Math Claude Opus 4.8 leads
Claude Opus 4.8: 78.4 (#13), Gemma 4 31B IT: 43.2 (#81)
| Benchmark | Claude Opus 4.8 | Gemma 4 31B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.3% | 73.3% |
| LMArena Math | 1487 | 1465 |
| FrontierMath (Tiers 1-3) | 80% | — |
| FrontierMath Tier 4 | 56.1% | — |
| MathArena Final-Answer Competitions | 91.8% | — |
| ProofBench | 69% | — |
| FrontierMath (Feb 2025 set) | 47.2% | — |
| FrontierMath Tier 4 (v1) | 31.3% | — |
Knowledge Claude Opus 4.8 leads
Claude Opus 4.8: 61.3 (#29), Gemma 4 31B IT: 37.9 (#151)
| Benchmark | Claude Opus 4.8 | Gemma 4 31B IT |
|---|---|---|
| GPQA Diamond | 91% | 75.8% |
| SimpleQA Verified | 53% | 10.4% |
| LMArena Expert | 1502 | 1465 |
| Vectara Hallucination Rate | — | 7.4% |
Multimodal Claude Opus 4.8 leads
Claude Opus 4.8: 42.9 (#26), Gemma 4 31B IT: 41.6 (#34)
| Benchmark | Claude Opus 4.8 | Gemma 4 31B IT |
|---|---|---|
| LMArena Vision | 1294 | 1277 |
| LMArena Document | 1475 | 1425 |
| Blueprint-Bench 2 | 14.5% | — |
| Furniture Assembly | 42.5% | — |
Multilingual Claude Opus 4.8 leads
Claude Opus 4.8: 55.2 (#33), Gemma 4 31B IT: 53.8 (#57)
| Benchmark | Claude Opus 4.8 | Gemma 4 31B IT |
|---|---|---|
| LMArena Non-English | 1450 | 1431 |
| LMArena Chinese | 1507 | 1476 |
| LMArena French | 1481 | 1435 |
| LMArena Russian | 1474 | 1460 |
| LMArena Spanish | 1466 | 1444 |
| LMArena German | 1472 | — |
| LMArena Japanese | 1440 | — |
| LMArena Korean | 1432 | — |
Instruction Following Claude Opus 4.8 leads
Claude Opus 4.8: 77.4 (#24), Gemma 4 31B IT: 75.5 (#61)
| Benchmark | Claude Opus 4.8 | Gemma 4 31B IT |
|---|---|---|
| LMArena Instruction Following | 1476 | 1433 |
Long Context Claude Opus 4.8 leads
Claude Opus 4.8: 45.4 (#35), Gemma 4 31B IT: 44.2 (#71)
| Benchmark | Claude Opus 4.8 | Gemma 4 31B IT |
|---|---|---|
| LMArena Longer Query | 1483 | 1446 |
Writing & Preference Claude Opus 4.8 leads
Claude Opus 4.8: 72.0 (#16), Gemma 4 31B IT: 60.5 (#96)
| Benchmark | Claude Opus 4.8 | Gemma 4 31B IT |
|---|---|---|
| LMArena Text | 1461 | 1443 |
| LMArena Creative Writing | 1454 | 1415 |
| EQ-Bench Creative Writing | 1840 | 1368 |
| EQ-Bench 4 | 1281 | 1120 |
| LMArena Multi-Turn | 1476 | 1452 |
Frequently asked questions
Is Claude Opus 4.8 better than Gemma 4 31B IT?
Claude Opus 4.8 is the stronger model overall, scoring 60.7 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 4.8's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 4.8 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 4.8 lists at $5 and $25.
Is Claude Opus 4.8 or Gemma 4 31B IT better for coding?
Claude Opus 4.8 scores higher on coding benchmarks: 59.9 versus 42.3 in the Noometry coding category.
Which has the bigger context window?
Claude Opus 4.8 does, with 1M tokens against 262K.
How many benchmarks do Claude Opus 4.8 and Gemma 4 31B IT share?
33 benchmarks have published results for both models. Claude Opus 4.8 has 65 scored results on Noometry and Gemma 4 31B IT has 35.