Model comparison
Claude Sonnet 4 vs Gemma 4 26B A4B IT
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.1 to 40.6 on the Noometry Index.
Last verified . 26 shared benchmarks.
GoogleSummary
- They share 26 benchmarks with published results for both. Claude Sonnet 4 scores higher in 2 categories and Gemma 4 26B A4B IT in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where Gemma 4 26B A4B IT leads 39.9 to 25.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 71.1% for Claude Sonnet 4 and 82.2% for Gemma 4 26B A4B IT.
- Gemma 4 26B A4B IT is cheaper at $0.0765 / $0.26 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- Gemma 4 26B A4B IT accepts more context: 262K tokens versus 200K.
- Gemma 4 26B A4B IT has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4 | Gemma 4 26B A4B IT | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 40.6 | 43.1 |
| Released | 2025-05-22 | 2026-04-02 |
| Weights | Proprietary | Open |
| Context window | 200K | 262K |
| Max output | 64K | 33K |
| Input $ / M tokens | $3 | $0.0765 |
| Output $ / M tokens | $15 | $0.26 |
| Results tracked | 58 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
Claude Sonnet 4: 44.0 (#70), Gemma 4 26B A4B IT: 38.8 (#156)
| Benchmark | Claude Sonnet 4 | Gemma 4 26B A4B IT |
|---|---|---|
| SciCode | 40% | 40% |
| WeirdML | 46.1% | 35.2% |
| LMArena Coding | 1414 | 1446 |
| ALE-Bench | 655.35 | 927.17 |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| LMArena WebDev | — | 1359 |
| GSO | 4.9% | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4: 38.3 (#29), Gemma 4 26B A4B IT: —
| Benchmark | Claude Sonnet 4 | Gemma 4 26B A4B IT |
|---|---|---|
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning Claude Sonnet 4 leads
Claude Sonnet 4: 23.0 (#169), Gemma 4 26B A4B IT: 21.1 (#205)
| Benchmark | Claude Sonnet 4 | Gemma 4 26B A4B IT |
|---|---|---|
| CritPt | 0.3% | 0% |
| LMArena Hard Prompts | 1372 | 1438 |
| DTBench | 77.1% | 74.9% |
| LMCA | 29% | 29.7% |
| Epoch Capabilities Index | 141.69 | 141.85 |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| Kagi LLM Benchmark | 73% | — |
| ARC-AGI-1 | 40% | — |
| Chess Puzzles | — | 6% |
| EnigmaEval | 3.1% | — |
| ForecastBench | 60.2 | — |
Math Gemma 4 26B A4B IT leads
Claude Sonnet 4: 41.5 (#71), Gemma 4 26B A4B IT: 45.7 (#61)
| Benchmark | Claude Sonnet 4 | Gemma 4 26B A4B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 82.2% |
| LMArena Math | 1375 | 1469 |
| Omni-MATH | 60.2% | — |
| MATH Level 5 | 84.4% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Gemma 4 26B A4B IT leads
Claude Sonnet 4: 41.6 (#99), Gemma 4 26B A4B IT: 45.6 (#79)
| Benchmark | Claude Sonnet 4 | Gemma 4 26B A4B IT |
|---|---|---|
| GPQA Diamond | 79.2% | 73.2% |
| Vectara Hallucination Rate | 10.3% | 5.2% |
| LMArena Expert | 1371 | 1447 |
| Humanity's Last Exam | 7.8% | — |
| MMLU-Pro | 84.3% | — |
| Confabulations | 13.2% | — |
| GPQA (HELM) | 70.6% | — |
Multimodal Gemma 4 26B A4B IT leads
Claude Sonnet 4: 25.6 (#116), Gemma 4 26B A4B IT: 39.9 (#43)
| Benchmark | Claude Sonnet 4 | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Vision | 1191 | 1260 |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual Gemma 4 26B A4B IT leads
Claude Sonnet 4: 46.9 (#151), Gemma 4 26B A4B IT: 53.3 (#68)
| Benchmark | Claude Sonnet 4 | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Non-English | 1333 | 1422 |
| LMArena Chinese | 1351 | 1495 |
| LMArena French | 1364 | 1459 |
| LMArena Russian | 1355 | 1434 |
| LMArena Spanish | 1356 | 1415 |
| LMArena German | 1331 | — |
| LMArena Japanese | 1301 | — |
| LMArena Korean | 1293 | — |
Instruction Following Gemma 4 26B A4B IT leads
Claude Sonnet 4: 71.8 (#141), Gemma 4 26B A4B IT: 75.0 (#78)
| Benchmark | Claude Sonnet 4 | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Instruction Following | 1375 | 1420 |
| IFEval | 84% | — |
Long Context Gemma 4 26B A4B IT leads
Claude Sonnet 4: 33.6 (#254), Gemma 4 26B A4B IT: 43.6 (#87)
| Benchmark | Claude Sonnet 4 | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Longer Query | 1398 | 1427 |
| Fiction.LiveBench | 46.9% | — |
Writing & Preference Gemma 4 26B A4B IT leads
Claude Sonnet 4: 57.3 (#127), Gemma 4 26B A4B IT: 58.8 (#110)
| Benchmark | Claude Sonnet 4 | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Text | 1351 | 1434 |
| LMArena Creative Writing | 1345 | 1401 |
| EQ-Bench Creative Writing | 1483 | 1305 |
| LMArena Multi-Turn | 1376 | 1442 |
| Short-Story Creative Writing | 81.4% | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is Claude Sonnet 4 better than Gemma 4 26B A4B IT?
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.1 to 40.6 on the Noometry Index.
Which is cheaper, Claude Sonnet 4 or Gemma 4 26B A4B IT?
Gemma 4 26B A4B IT is cheaper. It lists at $0.0765 per million input tokens and $0.26 per million output tokens; Claude Sonnet 4 lists at $3 and $15.
Is Claude Sonnet 4 or Gemma 4 26B A4B IT better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 44.0 versus 38.8 in the Noometry coding category.
Which has the bigger context window?
Gemma 4 26B A4B IT does, with 262K tokens against 200K.
How many benchmarks do Claude Sonnet 4 and Gemma 4 26B A4B IT share?
26 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Gemma 4 26B A4B IT has 28.