Model comparison
Claude 2.1 vs Claude 3 Haiku
Claude 2.1 and Claude 3 Haiku score almost the same on the Noometry Index (25.2 vs 25.9), so choose on price, context window or the category you care about most.
Last verified . 7 shared benchmarks.
Summary
- They share 7 benchmarks with published results for both. Claude 2.1 scores higher in 2 categories and Claude 3 Haiku in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude 2.1 leads 21.4 to 16.3.
Side by side
| Claude 2.1 | Claude 3 Haiku | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 25.2 | 25.9 |
| Released | 2023-11-21 | 2024-03-07 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude 2.1: 26.2 (#327), Claude 3 Haiku: 26.4 (#325)
| Benchmark | Claude 2.1 | Claude 3 Haiku |
|---|---|---|
| WeirdML | 7.1% | 9.8% |
| BigCodeBench Instruct | — | 39.4% |
| LMArena Coding | — | 1199 |
| BigCodeBench Complete | — | 50.1% |
| CadEval | — | 12% |
| HumanEval+ | — | 68.9% |
| MBPP+ | — | 68.8% |
Reasoning Claude 2.1 leads
Claude 2.1: 21.4 (#221), Claude 3 Haiku: 16.3 (#307)
| Benchmark | Claude 2.1 | Claude 3 Haiku |
|---|---|---|
| DTBench | 51% | 50.1% |
| Epoch Capabilities Index | 119.27 | 118.35 |
| ForecastBench | 54.2 | 53.2 |
| Kagi LLM Benchmark | — | 34.2% |
| LMArena Hard Prompts | — | 1174 |
| LMCA | — | 8.8% |
| WinoGrande | — | 74.2% |
Math Too close to call
Claude 2.1: 10.2 (#315), Claude 3 Haiku: 9.8 (#319)
| Benchmark | Claude 2.1 | Claude 3 Haiku |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | 1.8% |
| LMArena Math | — | 1188 |
| MATH Level 5 | — | 14.9% |
Knowledge Claude 3 Haiku leads
Claude 2.1: 15.4 (#292), Claude 3 Haiku: 17.3 (#285)
| Benchmark | Claude 2.1 | Claude 3 Haiku |
|---|---|---|
| GPQA Diamond | 33% | 36.3% |
| MMLU | 73.5% | 73.8% |
| Confabulations | — | 34.2% |
| LMArena Expert | — | 1148 |
Multimodal Not comparable
Claude 2.1: —, Claude 3 Haiku: 23.6 (#128)
| Benchmark | Claude 2.1 | Claude 3 Haiku |
|---|---|---|
| LMArena Vision | — | 950 |
| ScienceQA | — | 72% |
Multilingual Not comparable
Claude 2.1: —, Claude 3 Haiku: 36.0 (#243)
| Benchmark | Claude 2.1 | Claude 3 Haiku |
|---|---|---|
| LMArena Non-English | — | 1178 |
| LMArena Chinese | — | 1155 |
| LMArena French | — | 1195 |
| LMArena German | — | 1174 |
| LMArena Japanese | — | 1102 |
| LMArena Korean | — | 1109 |
| LMArena Russian | — | 1204 |
| LMArena Spanish | — | 1166 |
Instruction Following Not comparable
Claude 2.1: —, Claude 3 Haiku: 61.3 (#247)
| Benchmark | Claude 2.1 | Claude 3 Haiku |
|---|---|---|
| LMArena Instruction Following | — | 1173 |
Long Context Not comparable
Claude 2.1: —, Claude 3 Haiku: 36.1 (#237)
| Benchmark | Claude 2.1 | Claude 3 Haiku |
|---|---|---|
| LMArena Longer Query | — | 1190 |
Writing & Preference Not comparable
Claude 2.1: —, Claude 3 Haiku: 29.7 (#291)
| Benchmark | Claude 2.1 | Claude 3 Haiku |
|---|---|---|
| LMArena Text | — | 1195 |
| LMArena Creative Writing | — | 1157 |
| EQ-Bench Creative Writing | — | 717 |
| LMArena Multi-Turn | — | 1190 |
Frequently asked questions
Is Claude 2.1 better than Claude 3 Haiku?
Claude 2.1 and Claude 3 Haiku score almost the same on the Noometry Index (25.2 vs 25.9), so choose on price, context window or the category you care about most.
Is Claude 2.1 or Claude 3 Haiku better for coding?
They score almost the same on coding (26.2 vs 26.4); test both on your own repository before choosing.
How many benchmarks do Claude 2.1 and Claude 3 Haiku share?
7 benchmarks have published results for both models. Claude 2.1 has 7 scored results on Noometry and Claude 3 Haiku has 37.