Model comparison
Claude Opus 5 vs Gemma 3 27B
Claude Opus 5 is the stronger model overall, scoring 67.7 to 30.5 on the Noometry Index. Gemma 3 27B costs 100× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
GoogleSummary
- They share 27 benchmarks with published results for both. Claude Opus 5 scores higher in 10 categories and Gemma 3 27B in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 5 leads 86.1 to 24.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.9% for Claude Opus 5 and 22.5% for Gemma 3 27B.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $5 / $25 for Claude Opus 5.
- Claude Opus 5 accepts more context: 1M tokens versus 131K.
- Gemma 3 27B has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 5 | Gemma 3 27B | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 67.7 | 30.5 |
| Released | 2026-07-24 | 2025-03-11 |
| Weights | Proprietary | Open |
| Context window | 1M | 131K |
| Max output | 128K | 8K |
| Input $ / M tokens | $5 | $0.08 |
| Output $ / M tokens | $25 | $0.16 |
| Results tracked | 57 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 5 leads
Claude Opus 5: 67.0 (#5), Gemma 3 27B: 22.1 (#329)
| Benchmark | Claude Opus 5 | Gemma 3 27B |
|---|---|---|
| SciCode | 56.4% | 21.2% |
| LMArena Coding | 1533 | 1322 |
| DeepSWE | 73.6% | — |
| FrontierCode | 53.4% | — |
| Aider Polyglot | — | 4.9% |
| CursorBench | 46.6% | — |
| LMArena WebDev | 1694 | — |
| FrontierSWE | 52% | — |
| WeirdML | 91.8% | — |
| LiveBench Coding | — | 39.9% |
| ALE-Bench | 2,165 | — |
Agentic & Tool Use Claude Opus 5 leads
Claude Opus 5: 55.5 (#1), Gemma 3 27B: 24.9 (#105)
| Benchmark | Claude Opus 5 | Gemma 3 27B |
|---|---|---|
| APEX-Agents | 65.8% | — |
| Berkeley Function Calling Leaderboard | — | 29.5% |
| 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: 77.1 (#3), Gemma 3 27B: 16.3 (#297)
| Benchmark | Claude Opus 5 | Gemma 3 27B |
|---|---|---|
| CritPt | 29.1% | 0% |
| Chess Puzzles | 42% | 0% |
| LMArena Hard Prompts | 1525 | 1340 |
| DTBench | 97.9% | 52.5% |
| LMCA | 64.5% | 12.3% |
| Epoch Capabilities Index | 162.67 | 130.04 |
| ARC-AGI-2 | 90.4% | — |
| SimpleBench | 80.6% | — |
| Kagi LLM Benchmark | — | 40.4% |
| NYT Connections (extended) | 94.3% | — |
| ARC-AGI-1 | 97.5% | — |
| EBR-Bench | 45.7% | — |
| LiveBench Reasoning | — | 43.8% |
| Mystery Game Puzzles | 59% | — |
| LiveBench Data Analysis | — | 51.5% |
| Bench to the Future 3 | 0.12 | — |
| LiveBench | — | 50% |
Math Claude Opus 5 leads
Claude Opus 5: 86.1 (#6), Gemma 3 27B: 24.4 (#261)
| Benchmark | Claude Opus 5 | Gemma 3 27B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.9% | 22.5% |
| LMArena Math | 1533 | 1312 |
| FrontierMath (Tiers 1-3) | 85.6% | — |
| FrontierMath Tier 4 | 73.2% | — |
| ProofBench | 99% | — |
| LiveBench Math | — | 55.4% |
| MATH Level 5 | — | 74% |
Knowledge Claude Opus 5 leads
Claude Opus 5: 66.8 (#8), Gemma 3 27B: 25.4 (#256)
| Benchmark | Claude Opus 5 | Gemma 3 27B |
|---|---|---|
| GPQA Diamond | 93.9% | 47.7% |
| LMArena Expert | 1558 | 1303 |
| SimpleQA Verified | 59.9% | — |
| Confabulations | — | 40.3% |
| Vectara Hallucination Rate | — | 7.4% |
Multimodal Claude Opus 5 leads
Claude Opus 5: 51.1 (#6), Gemma 3 27B: 32.0 (#94)
| Benchmark | Claude Opus 5 | Gemma 3 27B |
|---|---|---|
| LMArena Vision | 1321 | 1165 |
| GeoBench | — | 52% |
| Blueprint-Bench 2 | 30.4% | — |
| Furniture Assembly | 60.8% | — |
| LMArena Document | 1516 | — |
Multilingual Claude Opus 5 leads
Claude Opus 5: 58.8 (#3), Gemma 3 27B: 47.0 (#150)
| Benchmark | Claude Opus 5 | Gemma 3 27B |
|---|---|---|
| LMArena Non-English | 1500 | 1334 |
| LMArena Chinese | 1575 | 1347 |
| LMArena French | 1522 | 1368 |
| LMArena German | 1522 | 1362 |
| LMArena Japanese | 1510 | 1287 |
| LMArena Korean | 1526 | 1308 |
| LMArena Russian | 1507 | 1349 |
| LMArena Spanish | 1519 | 1348 |
Instruction Following Claude Opus 5 leads
Claude Opus 5: 79.3 (#5), Gemma 3 27B: 70.8 (#155)
| Benchmark | Claude Opus 5 | Gemma 3 27B |
|---|---|---|
| LMArena Instruction Following | 1516 | 1321 |
| LiveBench Instruction Following | — | 74.9% |
Long Context Claude Opus 5 leads
Claude Opus 5: 46.5 (#20), Gemma 3 27B: 27.6 (#288)
| Benchmark | Claude Opus 5 | Gemma 3 27B |
|---|---|---|
| LMArena Longer Query | 1516 | 1333 |
| Fiction.LiveBench | — | 33.3% |
Writing & Preference Claude Opus 5 leads
Claude Opus 5: 79.3 (#2), Gemma 3 27B: 52.7 (#161)
| Benchmark | Claude Opus 5 | Gemma 3 27B |
|---|---|---|
| LMArena Text | 1506 | 1358 |
| LMArena Creative Writing | 1491 | 1346 |
| EQ-Bench Creative Writing | 2133 | 1266 |
| LMArena Multi-Turn | 1496 | 1344 |
| Short-Story Creative Writing | — | 79.9% |
| EQ-Bench 4 | 1385 | — |
| LiveBench Language | — | 34.6% |
Frequently asked questions
Is Claude Opus 5 better than Gemma 3 27B?
Claude Opus 5 is the stronger model overall, scoring 67.7 to 30.5 on the Noometry Index. Gemma 3 27B costs 100× 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 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 5 lists at $5 and $25.
Is Claude Opus 5 or Gemma 3 27B better for coding?
Claude Opus 5 scores higher on coding benchmarks: 67.0 versus 22.1 in the Noometry coding category.
Which has the bigger context window?
Claude Opus 5 does, with 1M tokens against 131K.
How many benchmarks do Claude Opus 5 and Gemma 3 27B share?
27 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and Gemma 3 27B has 43.