Model comparison
Claude 3 Haiku vs Yi-1.5-34B
Yi-1.5-34B is the stronger model overall, scoring 30.2 to 25.7 on the Noometry Index.
Last verified . 21 shared benchmarks.
Summary
- They share 21 benchmarks with published results for both. Claude 3 Haiku scores higher in 4 categories and Yi-1.5-34B in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Yi-1.5-34B leads 25.3 to 9.2.
- The biggest single-benchmark swing is MATH Level 5: 14.9% for Claude 3 Haiku and 25.5% for Yi-1.5-34B.
- Yi-1.5-34B has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Haiku | Yi-1.5-34B | |
|---|---|---|
| Provider | Anthropic | 01.AI |
| Noometry Index | 25.7 | 30.2 |
| Released | 2024-03-07 | 2024-05-13 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 37 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Yi-1.5-34B leads
Claude 3 Haiku: 26.1 (#320), Yi-1.5-34B: 31.9 (#267)
| Benchmark | Claude 3 Haiku | Yi-1.5-34B |
|---|---|---|
| BigCodeBench Instruct | 39.4% | 33.9% |
| LMArena Coding | 1199 | 1169 |
| BigCodeBench Complete | 50.1% | 43.8% |
| WeirdML | 9.8% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning Yi-1.5-34B leads
Claude 3 Haiku: 15.7 (#303), Yi-1.5-34B: 21.5 (#195)
| Benchmark | Claude 3 Haiku | Yi-1.5-34B |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1160 |
| Kagi LLM Benchmark | 34.2% | — |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.3 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math Yi-1.5-34B leads
Claude 3 Haiku: 9.2 (#313), Yi-1.5-34B: 25.3 (#248)
| Benchmark | Claude 3 Haiku | Yi-1.5-34B |
|---|---|---|
| LMArena Math | 1188 | 1182 |
| MATH Level 5 | 14.9% | 25.5% |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
Knowledge Claude 3 Haiku leads
Claude 3 Haiku: 17.3 (#280), Yi-1.5-34B: 14.8 (#290)
| Benchmark | Claude 3 Haiku | Yi-1.5-34B |
|---|---|---|
| GPQA Diamond | 36.3% | 32% |
| LMArena Expert | 1148 | 1144 |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.1 (#123), Yi-1.5-34B: —
| Benchmark | Claude 3 Haiku | Yi-1.5-34B |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Claude 3 Haiku leads
Claude 3 Haiku: 36.1 (#238), Yi-1.5-34B: 32.5 (#251)
| Benchmark | Claude 3 Haiku | Yi-1.5-34B |
|---|---|---|
| LMArena Non-English | 1178 | 1121 |
| LMArena Chinese | 1155 | 1213 |
| LMArena French | 1194 | 1155 |
| LMArena German | 1174 | 1111 |
| LMArena Japanese | 1102 | 1021 |
| LMArena Korean | 1108 | 1005 |
| LMArena Russian | 1204 | 1091 |
| LMArena Spanish | 1165 | 1120 |
Instruction Following Claude 3 Haiku leads
Claude 3 Haiku: 61.5 (#242), Yi-1.5-34B: 59.4 (#252)
| Benchmark | Claude 3 Haiku | Yi-1.5-34B |
|---|---|---|
| LMArena Instruction Following | 1174 | 1139 |
Long Context Claude 3 Haiku leads
Claude 3 Haiku: 36.1 (#232), Yi-1.5-34B: 34.6 (#243)
| Benchmark | Claude 3 Haiku | Yi-1.5-34B |
|---|---|---|
| LMArena Longer Query | 1191 | 1144 |
Writing & Preference Yi-1.5-34B leads
Claude 3 Haiku: 29.8 (#286), Yi-1.5-34B: 37.6 (#252)
| Benchmark | Claude 3 Haiku | Yi-1.5-34B |
|---|---|---|
| LMArena Text | 1195 | 1173 |
| LMArena Creative Writing | 1157 | 1135 |
| LMArena Multi-Turn | 1190 | 1153 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than Yi-1.5-34B?
Yi-1.5-34B is the stronger model overall, scoring 30.2 to 25.7 on the Noometry Index.
Is Claude 3 Haiku or Yi-1.5-34B better for coding?
Yi-1.5-34B scores higher on coding benchmarks: 31.9 versus 26.1 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Yi-1.5-34B share?
21 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Yi-1.5-34B has 21.