Model comparison
Claude 3.5 Haiku vs Gemma 4 26B A4B IT
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 29.2 on the Noometry Index.
Last verified . 23 shared benchmarks.
GoogleSummary
- They share 23 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 0 categories and Gemma 4 26B A4B IT in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 4 26B A4B IT leads 47.6 to 14.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.3% for Claude 3.5 Haiku and 82.2% for Gemma 4 26B A4B IT.
- Gemma 4 26B A4B IT has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Haiku | Gemma 4 26B A4B IT | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 29.2 | 43.5 |
| Released | 2024-10-22 | 2026-04-02 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.0675 |
| Output $ / M tokens | — | $0.23 |
| Results tracked | 49 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 26B A4B IT leads
Claude 3.5 Haiku: 32.9 (#265), Gemma 4 26B A4B IT: 39.0 (#164)
| Benchmark | Claude 3.5 Haiku | Gemma 4 26B A4B IT |
|---|---|---|
| SciCode | 27.4% | 40% |
| WeirdML | 30.7% | 35.2% |
| LMArena Coding | 1286 | 1447 |
| Aider Polyglot | 28% | — |
| LMArena WebDev | — | 1359 |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 51.4% | — |
| BigCodeBench Complete | 59% | — |
| CadEval | 32% | — |
| ALE-Bench | — | 927.17 |
Agentic & Tool Use Not comparable
Claude 3.5 Haiku: 28.0 (#95), Gemma 4 26B A4B IT: —
| Benchmark | Claude 3.5 Haiku | Gemma 4 26B A4B IT |
|---|---|---|
| BALROG | 19.3% | — |
Reasoning Gemma 4 26B A4B IT leads
Claude 3.5 Haiku: 17.7 (#290), Gemma 4 26B A4B IT: 21.8 (#213)
| Benchmark | Claude 3.5 Haiku | Gemma 4 26B A4B IT |
|---|---|---|
| CritPt | 0% | 0% |
| LMArena Hard Prompts | 1251 | 1439 |
| DTBench | 56.7% | 74.9% |
| Epoch Capabilities Index | 127.15 | 141.85 |
| Chess Puzzles | — | 6% |
| LiveBench Reasoning | 28.1% | — |
| LiveBench Data Analysis | 48.5% | — |
| LMCA | — | 29.7% |
| LiveBench | 43.5% | — |
Math Gemma 4 26B A4B IT leads
Claude 3.5 Haiku: 14.7 (#300), Gemma 4 26B A4B IT: 47.6 (#67)
| Benchmark | Claude 3.5 Haiku | Gemma 4 26B A4B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 82.2% |
| LMArena Math | 1244 | 1470 |
| Omni-MATH | 22.4% | — |
| LiveBench Math | 35.5% | — |
| MATH Level 5 | 46.4% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Gemma 4 26B A4B IT leads
Claude 3.5 Haiku: 18.7 (#281), Gemma 4 26B A4B IT: 45.7 (#85)
| Benchmark | Claude 3.5 Haiku | Gemma 4 26B A4B IT |
|---|---|---|
| GPQA Diamond | 38.1% | 73.2% |
| LMArena Expert | 1208 | 1447 |
| MMLU-Pro | 60.5% | — |
| Confabulations | 36.7% | — |
| Vectara Hallucination Rate | — | 5.2% |
| GPQA (HELM) | 36.3% | — |
| MMLU | 74.3% | — |
Multimodal Gemma 4 26B A4B IT leads
Claude 3.5 Haiku: 26.8 (#117), Gemma 4 26B A4B IT: 40.6 (#46)
| Benchmark | Claude 3.5 Haiku | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Vision | 1092 | 1260 |
| GeoBench | 34% | — |
Multilingual Gemma 4 26B A4B IT leads
Claude 3.5 Haiku: 40.0 (#218), Gemma 4 26B A4B IT: 53.1 (#71)
| Benchmark | Claude 3.5 Haiku | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Non-English | 1238 | 1421 |
| LMArena Chinese | 1229 | 1495 |
| LMArena French | 1264 | 1460 |
| LMArena Russian | 1253 | 1434 |
| LMArena Spanish | 1261 | 1417 |
| LMArena German | 1237 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1173 | — |
Instruction Following Gemma 4 26B A4B IT leads
Claude 3.5 Haiku: 62.9 (#234), Gemma 4 26B A4B IT: 74.8 (#82)
| Benchmark | Claude 3.5 Haiku | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Instruction Following | 1241 | 1420 |
| LiveBench Instruction Following | 61.9% | — |
| IFEval | 79.2% | — |
Long Context Gemma 4 26B A4B IT leads
Claude 3.5 Haiku: 38.3 (#200), Gemma 4 26B A4B IT: 43.6 (#91)
| Benchmark | Claude 3.5 Haiku | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Longer Query | 1261 | 1428 |
Writing & Preference Gemma 4 26B A4B IT leads
Claude 3.5 Haiku: 42.7 (#234), Gemma 4 26B A4B IT: 58.6 (#115)
| Benchmark | Claude 3.5 Haiku | Gemma 4 26B A4B IT |
|---|---|---|
| LMArena Text | 1255 | 1434 |
| LMArena Creative Writing | 1233 | 1402 |
| EQ-Bench Creative Writing | 1146 | 1305 |
| LMArena Multi-Turn | 1265 | 1441 |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 76% | — |
| LiveBench Language | 35.4% | — |
Frequently asked questions
Is Claude 3.5 Haiku better than Gemma 4 26B A4B IT?
Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 29.2 on the Noometry Index.
Is Claude 3.5 Haiku or Gemma 4 26B A4B IT better for coding?
Gemma 4 26B A4B IT scores higher on coding benchmarks: 39.0 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3.5 Haiku and Gemma 4 26B A4B IT share?
23 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Gemma 4 26B A4B IT has 28.