Model comparison
Gemini 2.5 Flash vs Gemma 4 26B A4B IT
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.1 to 39.0 on the Noometry Index.
Last verified . 24 shared benchmarks.
GoogleSummary
- They share 24 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 3 categories and Gemma 4 26B A4B IT in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemma 4 26B A4B IT leads 45.6 to 36.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 73.1% for Gemini 2.5 Flash 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 $0.30 / $2.50 for Gemini 2.5 Flash.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 262K.
- Gemma 4 26B A4B IT has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash | Gemma 4 26B A4B IT | |
|---|---|---|
| Provider | ||
| Noometry Index | 39.0 | 43.1 |
| Released | 2025-04-17 | 2026-04-02 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 66K | 33K |
| Input $ / M tokens | $0.30 | $0.0765 |
| Output $ / M tokens | $2.50 | $0.26 |
| Results tracked | 54 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 26B A4B IT leads
Gemini 2.5 Flash: 35.5 (#210), Gemma 4 26B A4B IT: 38.8 (#156)
| Benchmark | Gemini 2.5 Flash | Gemma 4 26B A4B IT |
|---|---|---|
| WeirdML | 41.9% | 35.2% |
| LMArena Coding | 1424 | 1446 |
| ALE-Bench | 661.88 | 927.17 |
| SWE-bench Verified (bash only) | 28.7% | — |
| Aider Polyglot | 55.1% | — |
| LMArena WebDev | — | 1359 |
| SciCode | — | 40% |
Agentic & Tool Use Not comparable
Gemini 2.5 Flash: 30.6 (#67), Gemma 4 26B A4B IT: —
| Benchmark | Gemini 2.5 Flash | Gemma 4 26B A4B IT |
|---|---|---|
| Terminal-Bench | 17.1% | — |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| BALROG | 33.5% | — |
| Vending-Bench 2 | 548.84 | — |
Reasoning Gemma 4 26B A4B IT leads
Gemini 2.5 Flash: 18.2 (#271), Gemma 4 26B A4B IT: 21.1 (#205)
| Benchmark | Gemini 2.5 Flash | Gemma 4 26B A4B IT |
|---|---|---|
| CritPt | 1.1% | 0% |
| LMArena Hard Prompts | 1422 | 1438 |
| DTBench | 76.5% | 74.9% |
| LMCA | 27.5% | 29.7% |
| Epoch Capabilities Index | 143.04 | 141.85 |
| ARC-AGI-2 | 2.5% | — |
| SimpleBench | 41.2% | — |
| Kagi LLM Benchmark | 56.8% | — |
| ARC-AGI-1 | 33.3% | — |
| Chess Puzzles | — | 6% |
| EnigmaEval | 2.7% | — |
| ForecastBench | 60.6 | — |
Math Gemma 4 26B A4B IT leads
Gemini 2.5 Flash: 38.1 (#87), Gemma 4 26B A4B IT: 45.7 (#61)
| Benchmark | Gemini 2.5 Flash | Gemma 4 26B A4B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | 82.2% |
| LMArena Math | 1415 | 1469 |
| Omni-MATH | 38.5% | — |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Gemma 4 26B A4B IT leads
Gemini 2.5 Flash: 36.1 (#162), Gemma 4 26B A4B IT: 45.6 (#79)
| Benchmark | Gemini 2.5 Flash | Gemma 4 26B A4B IT |
|---|---|---|
| Vectara Hallucination Rate | 7.8% | 5.2% |
| LMArena Expert | 1426 | 1447 |
| GPQA Diamond | — | 73.2% |
| Humanity's Last Exam | 12.1% | — |
| MMLU-Pro | 63.9% | — |
| Confabulations | 16.8% | — |
| GPQA (HELM) | 39% | — |
Multimodal Gemini 2.5 Flash leads
Gemini 2.5 Flash: 41.2 (#31), Gemma 4 26B A4B IT: 39.9 (#43)
| Benchmark | Gemini 2.5 Flash | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Vision | 1254 | 1260 |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| SpatialViz-Bench | 36.9% | — |
Multilingual Too close to call
Gemini 2.5 Flash: 52.5 (#83), Gemma 4 26B A4B IT: 53.3 (#68)
| Benchmark | Gemini 2.5 Flash | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Non-English | 1410 | 1422 |
| LMArena Chinese | 1450 | 1495 |
| LMArena French | 1433 | 1459 |
| LMArena Russian | 1415 | 1434 |
| LMArena Spanish | 1421 | 1415 |
| LMArena German | 1419 | — |
| LMArena Japanese | 1403 | — |
| LMArena Korean | 1385 | — |
Instruction Following Too close to call
Gemini 2.5 Flash: 75.9 (#50), Gemma 4 26B A4B IT: 75.0 (#78)
| Benchmark | Gemini 2.5 Flash | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Instruction Following | 1405 | 1420 |
| IFEval | 89.8% | — |
Long Context Gemini 2.5 Flash leads
Gemini 2.5 Flash: 47.5 (#16), Gemma 4 26B A4B IT: 43.6 (#87)
| Benchmark | Gemini 2.5 Flash | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Longer Query | 1419 | 1427 |
| Fiction.LiveBench | 77.8% | — |
Writing & Preference Gemma 4 26B A4B IT leads
Gemini 2.5 Flash: 54.0 (#153), Gemma 4 26B A4B IT: 58.8 (#110)
| Benchmark | Gemini 2.5 Flash | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Text | 1417 | 1434 |
| LMArena Creative Writing | 1400 | 1401 |
| EQ-Bench Creative Writing | 1137 | 1305 |
| LMArena Multi-Turn | 1408 | 1442 |
| Short-Story Creative Writing | 76.5% | — |
| WildBench | 81.7% | — |
Frequently asked questions
Is Gemini 2.5 Flash better than Gemma 4 26B A4B IT?
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.1 to 39.0 on the Noometry Index.
Which is cheaper, Gemini 2.5 Flash 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; Gemini 2.5 Flash lists at $0.30 and $2.50.
Is Gemini 2.5 Flash or Gemma 4 26B A4B IT better for coding?
Gemma 4 26B A4B IT scores higher on coding benchmarks: 38.8 versus 35.5 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash does, with 1.05M tokens against 262K.
How many benchmarks do Gemini 2.5 Flash and Gemma 4 26B A4B IT share?
24 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Gemma 4 26B A4B IT has 28.