Model comparison
Gemma 4 26B A4B IT vs Llama 4 Maverick
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 30.9 on the Noometry Index.
Last verified . 26 shared benchmarks.
Google
MetaSummary
- They share 26 benchmarks with published results for both. Gemma 4 26B A4B IT scores higher in 9 categories and Llama 4 Maverick in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 4 26B A4B IT leads 47.6 to 26.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 82.2% for Gemma 4 26B A4B IT and 20.6% for Llama 4 Maverick.
- Gemma 4 26B A4B IT is cheaper at $0.0675 / $0.23 per million input/output tokens, against $0.19 / $0.65 for Llama 4 Maverick.
- Gemma 4 26B A4B IT accepts more context: 262K tokens versus 128K.
Side by side
| Gemma 4 26B A4B IT | Llama 4 Maverick | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 43.5 | 30.9 |
| Released | 2026-04-02 | 2025-04-05 |
| Weights | Open | Open |
| Context window | 262K | 128K |
| Max output | 33K | 4K |
| Input $ / M tokens | $0.0675 | $0.19 |
| Output $ / M tokens | $0.23 | $0.65 |
| Results tracked | 28 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 39.0 (#164), Llama 4 Maverick: 26.6 (#324)
| Benchmark | Gemma 4 26B A4B IT | Llama 4 Maverick |
|---|---|---|
| SciCode | 40% | 33.1% |
| WeirdML | 35.2% | 24.5% |
| LMArena Coding | 1447 | 1302 |
| ALE-Bench | 927.17 | 172.97 |
| SWE-bench Verified (bash only) | — | 21% |
| Aider Polyglot | — | 15.6% |
| LMArena WebDev | 1359 | — |
| BigCodeBench Instruct | — | 49.7% |
| BigCodeBench Complete | — | 61.4% |
Agentic & Tool Use Not comparable
Gemma 4 26B A4B IT: —, Llama 4 Maverick: 28.2 (#91)
| Benchmark | Gemma 4 26B A4B IT | Llama 4 Maverick |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.3% |
Reasoning Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 21.8 (#213), Llama 4 Maverick: 10.1 (#342)
| Benchmark | Gemma 4 26B A4B IT | Llama 4 Maverick |
|---|---|---|
| CritPt | 0% | 0% |
| LMArena Hard Prompts | 1439 | 1281 |
| DTBench | 74.9% | 61.9% |
| LMCA | 29.7% | 15.9% |
| Epoch Capabilities Index | 141.85 | 132.2 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 27.7% |
| Kagi LLM Benchmark | — | 55.9% |
| NYT Connections (extended) | — | 8% |
| ARC-AGI-1 | — | 4.4% |
| Chess Puzzles | 6% | — |
| EnigmaEval | — | 0.6% |
| ForecastBench | — | 57.5 |
Math Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 47.6 (#67), Llama 4 Maverick: 26.0 (#262)
| Benchmark | Gemma 4 26B A4B IT | Llama 4 Maverick |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 82.2% | 20.6% |
| LMArena Math | 1470 | 1299 |
| Omni-MATH | — | 42.2% |
| MATH Level 5 | — | 73% |
| FrontierMath (Feb 2025 set) | — | 0.7% |
Knowledge Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 45.7 (#85), Llama 4 Maverick: 33.4 (#204)
| Benchmark | Gemma 4 26B A4B IT | Llama 4 Maverick |
|---|---|---|
| GPQA Diamond | 73.2% | 67% |
| Vectara Hallucination Rate | 5.2% | 8.2% |
| LMArena Expert | 1447 | 1259 |
| Humanity's Last Exam | — | 5.7% |
| MMLU-Pro | — | 81% |
| Confabulations | — | 22.6% |
| GPQA (HELM) | — | 65% |
Multimodal Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 40.6 (#46), Llama 4 Maverick: 31.6 (#105)
| Benchmark | Gemma 4 26B A4B IT | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | 1260 | 1142 |
| GeoBench | — | 52% |
| SpatialViz-Bench | — | 31.8% |
Multilingual Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 53.1 (#71), Llama 4 Maverick: 42.2 (#195)
| Benchmark | Gemma 4 26B A4B IT | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | 1421 | 1269 |
| LMArena Chinese | 1495 | 1277 |
| LMArena French | 1460 | 1259 |
| LMArena Russian | 1434 | 1286 |
| LMArena Spanish | 1417 | 1293 |
| LMArena German | — | 1291 |
| LMArena Japanese | — | 1207 |
| LMArena Korean | — | 1203 |
Instruction Following Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 74.8 (#82), Llama 4 Maverick: 71.7 (#146)
| Benchmark | Gemma 4 26B A4B IT | Llama 4 Maverick |
|---|---|---|
| LMArena Instruction Following | 1420 | 1267 |
| IFEval | — | 90.8% |
Long Context Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 43.6 (#91), Llama 4 Maverick: 31.4 (#279)
| Benchmark | Gemma 4 26B A4B IT | Llama 4 Maverick |
|---|---|---|
| LMArena Longer Query | 1428 | 1280 |
| Fiction.LiveBench | — | 46.2% |
Writing & Preference Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 58.6 (#115), Llama 4 Maverick: 38.8 (#252)
| Benchmark | Gemma 4 26B A4B IT | Llama 4 Maverick |
|---|---|---|
| LMArena Text | 1434 | 1287 |
| LMArena Creative Writing | 1402 | 1267 |
| EQ-Bench Creative Writing | 1305 | 860 |
| LMArena Multi-Turn | 1441 | 1289 |
| Short-Story Creative Writing | — | 62% |
| WildBench | — | 80% |
Frequently asked questions
Is Gemma 4 26B A4B IT better than Llama 4 Maverick?
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 30.9 on the Noometry Index.
Which is cheaper, Gemma 4 26B A4B IT or Llama 4 Maverick?
Gemma 4 26B A4B IT is cheaper. It lists at $0.0675 per million input tokens and $0.23 per million output tokens; Llama 4 Maverick lists at $0.19 and $0.65.
Is Gemma 4 26B A4B IT or Llama 4 Maverick better for coding?
Gemma 4 26B A4B IT scores higher on coding benchmarks: 39.0 versus 26.6 in the Noometry coding category.
Which has the bigger context window?
Gemma 4 26B A4B IT does, with 262K tokens against 128K.
How many benchmarks do Gemma 4 26B A4B IT and Llama 4 Maverick share?
26 benchmarks have published results for both models. Gemma 4 26B A4B IT has 28 scored results on Noometry and Llama 4 Maverick has 54.