Model comparison
Claude 3 Haiku vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 25.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Yi-Lightning in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Yi-Lightning leads 36.2 to 9.8.
Side by side
| Claude 3 Haiku | Yi-Lightning | |
|---|---|---|
| Provider | Anthropic | 01.AI |
| Noometry Index | 25.9 | 37.1 |
| Released | 2024-03-07 | 2024-12-02 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 37 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude 3 Haiku: 26.4 (#325), Yi-Lightning: 27.4 (#320)
| Benchmark | Claude 3 Haiku | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1199 | 1312 |
| Aider Polyglot | — | 12.9% |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning Yi-Lightning leads
Claude 3 Haiku: 16.3 (#307), Yi-Lightning: 25.9 (#139)
| Benchmark | Claude 3 Haiku | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1302 |
| Kagi LLM Benchmark | 34.2% | — |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.35 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math Yi-Lightning leads
Claude 3 Haiku: 9.8 (#319), Yi-Lightning: 36.2 (#172)
| Benchmark | Claude 3 Haiku | Yi-Lightning |
|---|---|---|
| LMArena Math | 1188 | 1300 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |
Knowledge Yi-Lightning leads
Claude 3 Haiku: 17.3 (#285), Yi-Lightning: 35.4 (#185)
| Benchmark | Claude 3 Haiku | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1148 | 1286 |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.6 (#128), Yi-Lightning: —
| Benchmark | Claude 3 Haiku | Yi-Lightning |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Yi-Lightning leads
Claude 3 Haiku: 36.0 (#243), Yi-Lightning: 42.2 (#196)
| Benchmark | Claude 3 Haiku | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1178 | 1269 |
| LMArena Chinese | 1155 | 1320 |
| LMArena French | 1195 | 1305 |
| LMArena German | 1174 | 1267 |
| LMArena Japanese | 1102 | 1228 |
| LMArena Korean | 1109 | 1192 |
| LMArena Russian | 1204 | 1255 |
| LMArena Spanish | 1166 | 1315 |
Instruction Following Yi-Lightning leads
Claude 3 Haiku: 61.3 (#247), Yi-Lightning: 67.4 (#196)
| Benchmark | Claude 3 Haiku | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1173 | 1278 |
Long Context Yi-Lightning leads
Claude 3 Haiku: 36.1 (#237), Yi-Lightning: 39.4 (#181)
| Benchmark | Claude 3 Haiku | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1190 | 1297 |
Writing & Preference Yi-Lightning leads
Claude 3 Haiku: 29.7 (#291), Yi-Lightning: 50.2 (#184)
| Benchmark | Claude 3 Haiku | Yi-Lightning |
|---|---|---|
| LMArena Text | 1195 | 1302 |
| LMArena Creative Writing | 1157 | 1280 |
| LMArena Multi-Turn | 1190 | 1311 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or Yi-Lightning better for coding?
They score almost the same on coding (26.4 vs 27.4); test both on your own repository before choosing.
How many benchmarks do Claude 3 Haiku and Yi-Lightning share?
17 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Yi-Lightning has 18.