Model comparison
Claude 3 Haiku vs Gemini 1.0 Pro
Gemini 1.0 Pro is the stronger model overall, scoring 27.1 to 25.7 on the Noometry Index.
Last verified . 24 shared benchmarks.
GoogleSummary
- They share 24 benchmarks with published results for both. Claude 3 Haiku scores higher in 5 categories and Gemini 1.0 Pro in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 1.0 Pro leads 36.2 to 29.8.
Side by side
| Claude 3 Haiku | Gemini 1.0 Pro | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 25.7 | 27.1 |
| Released | 2024-03-07 | 2023-12-13 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 37 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 1.0 Pro leads
Claude 3 Haiku: 26.1 (#320), Gemini 1.0 Pro: 31.6 (#270)
| Benchmark | Claude 3 Haiku | Gemini 1.0 Pro |
|---|---|---|
| LMArena Coding | 1199 | 1108 |
| HumanEval+ | 68.9% | 55.5% |
| MBPP+ | 68.8% | 61.4% |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
Reasoning Too close to call
Claude 3 Haiku: 15.7 (#303), Gemini 1.0 Pro: 16.4 (#292)
| Benchmark | Claude 3 Haiku | Gemini 1.0 Pro |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1109 |
| DTBench | 50.1% | 45.9% |
| Epoch Capabilities Index | 118.3 | 116.97 |
| Kagi LLM Benchmark | 34.2% | — |
| LMCA | 8.8% | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math Too close to call
Claude 3 Haiku: 9.2 (#313), Gemini 1.0 Pro: 8.7 (#315)
| Benchmark | Claude 3 Haiku | Gemini 1.0 Pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | 1.1% |
| LMArena Math | 1188 | 1132 |
| MATH Level 5 | 14.9% | 11.2% |
Knowledge Claude 3 Haiku leads
Claude 3 Haiku: 17.3 (#280), Gemini 1.0 Pro: 15.5 (#286)
| Benchmark | Claude 3 Haiku | Gemini 1.0 Pro |
|---|---|---|
| GPQA Diamond | 36.3% | 34% |
| LMArena Expert | 1148 | 1059 |
| MMLU | 73.8% | 70% |
| Confabulations | 34.2% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.1 (#123), Gemini 1.0 Pro: —
| Benchmark | Claude 3 Haiku | Gemini 1.0 Pro |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Claude 3 Haiku leads
Claude 3 Haiku: 36.1 (#238), Gemini 1.0 Pro: 33.5 (#247)
| Benchmark | Claude 3 Haiku | Gemini 1.0 Pro |
|---|---|---|
| LMArena Non-English | 1178 | 1138 |
| LMArena Chinese | 1155 | 1124 |
| LMArena French | 1194 | 1144 |
| LMArena German | 1174 | 1125 |
| LMArena Japanese | 1102 | 1023 |
| LMArena Russian | 1204 | 1186 |
| LMArena Spanish | 1165 | 1118 |
| LMArena Korean | 1108 | — |
Instruction Following Claude 3 Haiku leads
Claude 3 Haiku: 61.5 (#242), Gemini 1.0 Pro: 57.9 (#262)
| Benchmark | Claude 3 Haiku | Gemini 1.0 Pro |
|---|---|---|
| LMArena Instruction Following | 1174 | 1114 |
Long Context Claude 3 Haiku leads
Claude 3 Haiku: 36.1 (#232), Gemini 1.0 Pro: 34.3 (#244)
| Benchmark | Claude 3 Haiku | Gemini 1.0 Pro |
|---|---|---|
| LMArena Longer Query | 1191 | 1132 |
Writing & Preference Gemini 1.0 Pro leads
Claude 3 Haiku: 29.8 (#286), Gemini 1.0 Pro: 36.2 (#259)
| Benchmark | Claude 3 Haiku | Gemini 1.0 Pro |
|---|---|---|
| LMArena Text | 1195 | 1149 |
| LMArena Creative Writing | 1157 | 1130 |
| LMArena Multi-Turn | 1190 | 1139 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than Gemini 1.0 Pro?
Gemini 1.0 Pro is the stronger model overall, scoring 27.1 to 25.7 on the Noometry Index.
Is Claude 3 Haiku or Gemini 1.0 Pro better for coding?
Gemini 1.0 Pro scores higher on coding benchmarks: 31.6 versus 26.1 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Gemini 1.0 Pro share?
24 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Gemini 1.0 Pro has 24.