Model comparison
Claude Opus 4 vs Gemma 3 27B
Claude Opus 4 is the stronger model overall, scoring 43.1 to 30.8 on the Noometry Index. Gemma 3 27B costs 300× less per token, which makes it the better buy when Claude Opus 4'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 scores higher in 9 categories and Gemma 3 27B in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Opus 4 leads 47.2 to 22.5.
- The biggest single-benchmark swing is Aider Polyglot: 72% for Claude Opus 4 and 4.9% for Gemma 3 27B.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $15 / $75 for Claude Opus 4.
- Claude Opus 4 accepts more context: 200K tokens versus 131K.
- Gemma 3 27B has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4 | Gemma 3 27B | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 43.1 | 30.8 |
| Released | 2025-05-22 | 2025-03-11 |
| Weights | Proprietary | Open |
| Context window | 200K | 131K |
| Max output | 32K | 8K |
| Input $ / M tokens | $15 | $0.08 |
| Output $ / M tokens | $75 | $0.16 |
| Results tracked | 56 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4 leads
Claude Opus 4: 47.2 (#62), Gemma 3 27B: 22.5 (#334)
| Benchmark | Claude Opus 4 | Gemma 3 27B |
|---|---|---|
| Aider Polyglot | 72% | 4.9% |
| LMArena Coding | 1442 | 1322 |
| SWE-bench Verified | 70.7% | — |
| SWE-bench Verified (bash only) | 67.6% | — |
| SciCode | — | 21.2% |
| GSO | 6.9% | — |
| WeirdML | 43.7% | — |
| LiveBench Coding | — | 39.9% |
| AlgoTune | 1.33 | — |
Agentic & Tool Use Claude Opus 4 leads
Claude Opus 4: 34.8 (#42), Gemma 3 27B: 25.1 (#110)
| Benchmark | Claude Opus 4 | Gemma 3 27B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 29.5% |
| Cybench | 38% | — |
| DeepResearch Bench | 46.8% | — |
| LMArena Search | 1127 | — |
| METR Time Horizons | 63.9% | — |
Reasoning Claude Opus 4 leads
Claude Opus 4: 27.3 (#121), Gemma 3 27B: 16.7 (#301)
| Benchmark | Claude Opus 4 | Gemma 3 27B |
|---|---|---|
| Kagi LLM Benchmark | 74.3% | 40.4% |
| CritPt | 0.3% | 0% |
| LMArena Hard Prompts | 1399 | 1340 |
| DTBench | 81.6% | 52.5% |
| LMCA | 37.4% | 12.3% |
| Epoch Capabilities Index | 142.67 | 130.04 |
| ARC-AGI-2 | 8.6% | — |
| SimpleBench | 58.8% | — |
| ARC-AGI-1 | 35.7% | — |
| Chess Puzzles | — | 0% |
| EnigmaEval | 5.6% | — |
| LiveBench Reasoning | — | 43.8% |
| LiveBench Data Analysis | — | 51.5% |
| ForecastBench | 61.1 | — |
| LiveBench | — | 50% |
Math Claude Opus 4 leads
Claude Opus 4: 42.0 (#86), Gemma 3 27B: 25.9 (#265)
| Benchmark | Claude Opus 4 | Gemma 3 27B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 64.4% | 22.5% |
| LMArena Math | 1390 | 1312 |
| MATH Level 5 | 85% | 74% |
| Omni-MATH | 61.6% | — |
| LiveBench Math | — | 55.4% |
| FrontierMath (Feb 2025 set) | 4.5% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Opus 4 leads
Claude Opus 4: 44.0 (#88), Gemma 3 27B: 25.5 (#261)
| Benchmark | Claude Opus 4 | Gemma 3 27B |
|---|---|---|
| GPQA Diamond | 76.3% | 47.7% |
| Confabulations | 15.9% | 40.3% |
| Vectara Hallucination Rate | 12% | 7.4% |
| LMArena Expert | 1386 | 1304 |
| Humanity's Last Exam | 10.7% | — |
| MMLU-Pro | 87.5% | — |
| GPQA (HELM) | 70.8% | — |
Multimodal Gemma 3 27B leads
Claude Opus 4: 31.5 (#106), Gemma 3 27B: 32.6 (#100)
| Benchmark | Claude Opus 4 | Gemma 3 27B |
|---|---|---|
| LMArena Vision | 1192 | 1164 |
| GeoBench | 49% | 52% |
| VPCT | 38% | — |
Multilingual Claude Opus 4 leads
Claude Opus 4: 48.8 (#138), Gemma 3 27B: 46.9 (#155)
| Benchmark | Claude Opus 4 | Gemma 3 27B |
|---|---|---|
| LMArena Non-English | 1362 | 1334 |
| LMArena Chinese | 1386 | 1346 |
| LMArena French | 1372 | 1368 |
| LMArena German | 1391 | 1362 |
| LMArena Japanese | 1331 | 1287 |
| LMArena Korean | 1321 | 1308 |
| LMArena Russian | 1392 | 1349 |
| LMArena Spanish | 1389 | 1349 |
Instruction Following Claude Opus 4 leads
Claude Opus 4: 77.1 (#28), Gemma 3 27B: 70.6 (#160)
| Benchmark | Claude Opus 4 | Gemma 3 27B |
|---|---|---|
| LMArena Instruction Following | 1406 | 1321 |
| LiveBench Instruction Following | — | 74.9% |
| IFEval | 91.8% | — |
Long Context Claude Opus 4 leads
Claude Opus 4: 39.6 (#172), Gemma 3 27B: 27.6 (#293)
| Benchmark | Claude Opus 4 | Gemma 3 27B |
|---|---|---|
| Fiction.LiveBench | 61.1% | 33.3% |
| LMArena Longer Query | 1422 | 1333 |
Writing & Preference Claude Opus 4 leads
Claude Opus 4: 61.2 (#89), Gemma 3 27B: 52.5 (#168)
| Benchmark | Claude Opus 4 | Gemma 3 27B |
|---|---|---|
| LMArena Text | 1377 | 1358 |
| LMArena Creative Writing | 1387 | 1346 |
| Short-Story Creative Writing | 83.6% | 79.9% |
| EQ-Bench Creative Writing | 1580 | 1266 |
| LMArena Multi-Turn | 1396 | 1345 |
| WildBench | 85.2% | — |
| LiveBench Language | — | 34.6% |
Frequently asked questions
Is Claude Opus 4 better than Gemma 3 27B?
Claude Opus 4 is the stronger model overall, scoring 43.1 to 30.8 on the Noometry Index. Gemma 3 27B costs 300× less per token, which makes it the better buy when Claude Opus 4's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 4 or Gemma 3 27B?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; Claude Opus 4 lists at $15 and $75.
Is Claude Opus 4 or Gemma 3 27B better for coding?
Claude Opus 4 scores higher on coding benchmarks: 47.2 versus 22.5 in the Noometry coding category.
Which has the bigger context window?
Claude Opus 4 does, with 200K tokens against 131K.
How many benchmarks do Claude Opus 4 and Gemma 3 27B share?
33 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and Gemma 3 27B has 43.