Model comparison
Claude 3 Haiku vs Yi-34B
Yi-34B is the stronger model overall, scoring 27.8 to 25.9 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-34B in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Yi-34B leads 21.6 to 9.8.
- The biggest single-benchmark swing is GPQA Diamond: 36.3% for Claude 3 Haiku and 14.7% for Yi-34B.
- Yi-34B has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Haiku | Yi-34B | |
|---|---|---|
| Provider | Anthropic | 01.AI |
| Noometry Index | 25.9 | 27.8 |
| Released | 2024-03-07 | 2023-11-02 |
| 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 Yi-34B leads
Claude 3 Haiku: 26.4 (#325), Yi-34B: 32.3 (#274)
| Benchmark | Claude 3 Haiku | Yi-34B |
|---|---|---|
| LMArena Coding | 1199 | 1112 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning Yi-34B leads
Claude 3 Haiku: 16.3 (#307), Yi-34B: 21.2 (#226)
| Benchmark | Claude 3 Haiku | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1104 |
| Epoch Capabilities Index | 118.35 | 117.39 |
| Kagi LLM Benchmark | 34.2% | — |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| BIG-Bench Hard | — | 71.7% |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math Yi-34B leads
Claude 3 Haiku: 9.8 (#319), Yi-34B: 21.6 (#282)
| Benchmark | Claude 3 Haiku | Yi-34B |
|---|---|---|
| LMArena Math | 1188 | 1114 |
| MATH Level 5 | 14.9% | 5.1% |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| GSM8K | — | 76% |
Knowledge Claude 3 Haiku leads
Claude 3 Haiku: 17.3 (#285), Yi-34B: 7.5 (#309)
| Benchmark | Claude 3 Haiku | Yi-34B |
|---|---|---|
| GPQA Diamond | 36.3% | 14.7% |
| LMArena Expert | 1148 | 1061 |
| MMLU | 73.8% | 76.3% |
| Confabulations | 34.2% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.6 (#128), Yi-34B: —
| Benchmark | Claude 3 Haiku | Yi-34B |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Claude 3 Haiku leads
Claude 3 Haiku: 36.0 (#243), Yi-34B: 29.7 (#264)
| Benchmark | Claude 3 Haiku | Yi-34B |
|---|---|---|
| LMArena Non-English | 1178 | 1079 |
| LMArena Chinese | 1155 | 1176 |
| LMArena French | 1195 | 1081 |
| LMArena German | 1174 | 1042 |
| LMArena Japanese | 1102 | 993 |
| LMArena Korean | 1109 | 959 |
| LMArena Russian | 1204 | 1050 |
| LMArena Spanish | 1166 | 1070 |
Instruction Following Claude 3 Haiku leads
Claude 3 Haiku: 61.3 (#247), Yi-34B: 56.2 (#274)
| Benchmark | Claude 3 Haiku | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1173 | 1091 |
Long Context Claude 3 Haiku leads
Claude 3 Haiku: 36.1 (#237), Yi-34B: 33.2 (#264)
| Benchmark | Claude 3 Haiku | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1190 | 1094 |
Writing & Preference Yi-34B leads
Claude 3 Haiku: 29.7 (#291), Yi-34B: 34.1 (#273)
| Benchmark | Claude 3 Haiku | Yi-34B |
|---|---|---|
| LMArena Text | 1195 | 1129 |
| LMArena Creative Writing | 1157 | 1108 |
| LMArena Multi-Turn | 1190 | 1113 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than Yi-34B?
Yi-34B is the stronger model overall, scoring 27.8 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or Yi-34B better for coding?
Yi-34B scores higher on coding benchmarks: 32.3 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Yi-34B share?
21 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Yi-34B has 23.