Model comparison
Claude 3.5 Haiku vs Gemma 3 12B
Gemma 3 12B is the stronger model overall, scoring 32.1 to 29.2 on the Noometry Index.
Last verified . 19 shared benchmarks.
GoogleSummary
- They share 19 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 3 categories and Gemma 3 12B in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemma 3 12B leads 26.5 to 18.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.3% for Claude 3.5 Haiku and 16.7% for Gemma 3 12B.
- Gemma 3 12B has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Haiku | Gemma 3 12B | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 29.2 | 32.1 |
| Released | 2024-10-22 | 2025-03-12 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.15 |
| Results tracked | 49 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.5 Haiku leads
Claude 3.5 Haiku: 32.9 (#265), Gemma 3 12B: 31.7 (#280)
| Benchmark | Claude 3.5 Haiku | Gemma 3 12B |
|---|---|---|
| SciCode | 27.4% | 17.4% |
| LMArena Coding | 1286 | 1281 |
| Aider Polyglot | 28% | — |
| WeirdML | 30.7% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 51.4% | — |
| BigCodeBench Complete | 59% | — |
| CadEval | 32% | — |
Agentic & Tool Use Claude 3.5 Haiku leads
Claude 3.5 Haiku: 28.0 (#95), Gemma 3 12B: 25.5 (#108)
| Benchmark | Claude 3.5 Haiku | Gemma 3 12B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 30.4% |
| BALROG | 19.3% | — |
Reasoning Claude 3.5 Haiku leads
Claude 3.5 Haiku: 17.7 (#290), Gemma 3 12B: 15.7 (#313)
| Benchmark | Claude 3.5 Haiku | Gemma 3 12B |
|---|---|---|
| CritPt | 0% | 0% |
| LMArena Hard Prompts | 1251 | 1309 |
| DTBench | 56.7% | 48.8% |
| Epoch Capabilities Index | 127.15 | 123.5 |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | 28.1% | — |
| LiveBench Data Analysis | 48.5% | — |
| LMCA | — | 4.5% |
| LiveBench | 43.5% | — |
Math Gemma 3 12B leads
Claude 3.5 Haiku: 14.7 (#300), Gemma 3 12B: 22.3 (#279)
| Benchmark | Claude 3.5 Haiku | Gemma 3 12B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 16.7% |
| LMArena Math | 1244 | 1307 |
| Omni-MATH | 22.4% | — |
| LiveBench Math | 35.5% | — |
| MATH Level 5 | 46.4% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Gemma 3 12B leads
Claude 3.5 Haiku: 18.7 (#281), Gemma 3 12B: 26.5 (#257)
| Benchmark | Claude 3.5 Haiku | Gemma 3 12B |
|---|---|---|
| GPQA Diamond | 38.1% | 39.5% |
| LMArena Expert | 1208 | 1248 |
| MMLU-Pro | 60.5% | — |
| Confabulations | 36.7% | — |
| Vectara Hallucination Rate | — | 4.4% |
| GPQA (HELM) | 36.3% | — |
| MMLU | 74.3% | — |
Multimodal Not comparable
Claude 3.5 Haiku: 26.8 (#117), Gemma 3 12B: —
| Benchmark | Claude 3.5 Haiku | Gemma 3 12B |
|---|---|---|
| LMArena Vision | 1092 | — |
| GeoBench | 34% | — |
| MindCube | — | 46.7% |
Multilingual Gemma 3 12B leads
Claude 3.5 Haiku: 40.0 (#218), Gemma 3 12B: 45.7 (#165)
| Benchmark | Claude 3.5 Haiku | Gemma 3 12B |
|---|---|---|
| LMArena Non-English | 1238 | 1318 |
| LMArena German | 1237 | 1370 |
| LMArena Russian | 1253 | 1335 |
| LMArena Chinese | 1229 | — |
| LMArena French | 1264 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1173 | — |
| LMArena Spanish | 1261 | — |
Instruction Following Gemma 3 12B leads
Claude 3.5 Haiku: 62.9 (#234), Gemma 3 12B: 68.6 (#186)
| Benchmark | Claude 3.5 Haiku | Gemma 3 12B |
|---|---|---|
| LMArena Instruction Following | 1241 | 1299 |
| LiveBench Instruction Following | 61.9% | — |
| IFEval | 79.2% | — |
Long Context Gemma 3 12B leads
Claude 3.5 Haiku: 38.3 (#200), Gemma 3 12B: 40.0 (#162)
| Benchmark | Claude 3.5 Haiku | Gemma 3 12B |
|---|---|---|
| LMArena Longer Query | 1261 | 1317 |
Writing & Preference Gemma 3 12B leads
Claude 3.5 Haiku: 42.7 (#234), Gemma 3 12B: 47.5 (#209)
| Benchmark | Claude 3.5 Haiku | Gemma 3 12B |
|---|---|---|
| LMArena Text | 1255 | 1334 |
| LMArena Creative Writing | 1233 | 1331 |
| EQ-Bench Creative Writing | 1146 | 1126 |
| LMArena Multi-Turn | 1265 | 1334 |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 76% | — |
| LiveBench Language | 35.4% | — |
Frequently asked questions
Is Claude 3.5 Haiku better than Gemma 3 12B?
Gemma 3 12B is the stronger model overall, scoring 32.1 to 29.2 on the Noometry Index.
Is Claude 3.5 Haiku or Gemma 3 12B better for coding?
Claude 3.5 Haiku scores higher on coding benchmarks: 32.9 versus 31.7 in the Noometry coding category.
How many benchmarks do Claude 3.5 Haiku and Gemma 3 12B share?
19 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Gemma 3 12B has 24.