Model comparison
Claude 3 Haiku vs Gemma 2B
Gemma 2B is the stronger model overall, scoring 29.6 to 25.9 on the Noometry Index.
Last verified . 16 shared benchmarks.
GoogleSummary
- They share 16 benchmarks with published results for both. Claude 3 Haiku scores higher in 4 categories and Gemma 2B in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 2B leads 30.0 to 9.8.
- Gemma 2B has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Haiku | Gemma 2B | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 25.9 | 29.6 |
| Released | 2024-03-07 | 2024-02-21 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 37 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 2B leads
Claude 3 Haiku: 26.4 (#325), Gemma 2B: 29.4 (#305)
| Benchmark | Claude 3 Haiku | Gemma 2B |
|---|---|---|
| LMArena Coding | 1199 | 1010 |
| HumanEval+ | 68.9% | 20.7% |
| MBPP+ | 68.8% | 34.1% |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
Reasoning Gemma 2B leads
Claude 3 Haiku: 16.3 (#307), Gemma 2B: 18.8 (#275)
| Benchmark | Claude 3 Haiku | Gemma 2B |
|---|---|---|
| LMArena Hard Prompts | 1174 | 989 |
| Epoch Capabilities Index | 118.35 | 94.2 |
| WinoGrande | 74.2% | 65.4% |
| Kagi LLM Benchmark | 34.2% | — |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| BIG-Bench Hard | — | 35.2% |
| ForecastBench | 53.2 | — |
| HellaSwag | — | 71.4% |
| PIQA | — | 77.3% |
Math Gemma 2B leads
Claude 3 Haiku: 9.8 (#319), Gemma 2B: 30.0 (#239)
| Benchmark | Claude 3 Haiku | Gemma 2B |
|---|---|---|
| LMArena Math | 1188 | 1009 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |
| GSM8K | — | 17.7% |
Knowledge Not comparable
Claude 3 Haiku: 17.3 (#285), Gemma 2B: —
| Benchmark | Claude 3 Haiku | Gemma 2B |
|---|---|---|
| MMLU | 73.8% | 42.3% |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| LMArena Expert | 1148 | — |
| ARC (AI2) Challenge | — | 42.1% |
| BoolQ | — | 69.4% |
| TriviaQA | — | 53.2% |
Multimodal Not comparable
Claude 3 Haiku: 23.6 (#128), Gemma 2B: —
| Benchmark | Claude 3 Haiku | Gemma 2B |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Claude 3 Haiku leads
Claude 3 Haiku: 36.0 (#243), Gemma 2B: 23.0 (#294)
| Benchmark | Claude 3 Haiku | Gemma 2B |
|---|---|---|
| LMArena Non-English | 1178 | 958 |
| LMArena Chinese | 1155 | 986 |
| LMArena Russian | 1204 | 937 |
| LMArena French | 1195 | — |
| LMArena German | 1174 | — |
| LMArena Japanese | 1102 | — |
| LMArena Korean | 1109 | — |
| LMArena Spanish | 1166 | — |
Instruction Following Claude 3 Haiku leads
Claude 3 Haiku: 61.3 (#247), Gemma 2B: 48.5 (#302)
| Benchmark | Claude 3 Haiku | Gemma 2B |
|---|---|---|
| LMArena Instruction Following | 1173 | 970 |
Long Context Claude 3 Haiku leads
Claude 3 Haiku: 36.1 (#237), Gemma 2B: 29.9 (#291)
| Benchmark | Claude 3 Haiku | Gemma 2B |
|---|---|---|
| LMArena Longer Query | 1190 | 981 |
Writing & Preference Claude 3 Haiku leads
Claude 3 Haiku: 29.7 (#291), Gemma 2B: 24.0 (#308)
| Benchmark | Claude 3 Haiku | Gemma 2B |
|---|---|---|
| LMArena Text | 1195 | 1002 |
| LMArena Creative Writing | 1157 | 987 |
| LMArena Multi-Turn | 1190 | 945 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than Gemma 2B?
Gemma 2B is the stronger model overall, scoring 29.6 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or Gemma 2B better for coding?
Gemma 2B scores higher on coding benchmarks: 29.4 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Gemma 2B share?
16 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Gemma 2B has 23.