Model comparison
Claude 3 Haiku vs ERNIE 5.1
ERNIE 5.1 is the stronger model overall, scoring 43.1 to 25.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
BaiduSummary
- They share 17 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and ERNIE 5.1 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.3 to 29.8.
Side by side
| Claude 3 Haiku | ERNIE 5.1 | |
|---|---|---|
| Provider | Anthropic | Baidu |
| Noometry Index | 25.7 | 43.1 |
| Released | 2024-03-07 | — |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 37 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding ERNIE 5.1 leads
Claude 3 Haiku: 26.1 (#320), ERNIE 5.1: 43.4 (#78)
| Benchmark | Claude 3 Haiku | ERNIE 5.1 |
|---|---|---|
| LMArena Coding | 1199 | 1488 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Agentic & Tool Use Not comparable
Claude 3 Haiku: —, ERNIE 5.1: —
| Benchmark | Claude 3 Haiku | ERNIE 5.1 |
|---|---|---|
| LMArena Search | — | 1227 |
Reasoning ERNIE 5.1 leads
Claude 3 Haiku: 15.7 (#303), ERNIE 5.1: 20.9 (#209)
| Benchmark | Claude 3 Haiku | ERNIE 5.1 |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1481 |
| Kagi LLM Benchmark | 34.2% | — |
| NYT Connections (extended) | — | 23.4% |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.3 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math ERNIE 5.1 leads
Claude 3 Haiku: 9.2 (#313), ERNIE 5.1: 37.5 (#96)
| Benchmark | Claude 3 Haiku | ERNIE 5.1 |
|---|---|---|
| LMArena Math | 1188 | 1481 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |
Knowledge ERNIE 5.1 leads
Claude 3 Haiku: 17.3 (#280), ERNIE 5.1: 41.2 (#103)
| Benchmark | Claude 3 Haiku | ERNIE 5.1 |
|---|---|---|
| LMArena Expert | 1148 | 1491 |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.1 (#123), ERNIE 5.1: —
| Benchmark | Claude 3 Haiku | ERNIE 5.1 |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual ERNIE 5.1 leads
Claude 3 Haiku: 36.1 (#238), ERNIE 5.1: 55.7 (#28)
| Benchmark | Claude 3 Haiku | ERNIE 5.1 |
|---|---|---|
| LMArena Non-English | 1178 | 1455 |
| LMArena Chinese | 1155 | 1507 |
| LMArena French | 1194 | 1486 |
| LMArena German | 1174 | 1470 |
| LMArena Japanese | 1102 | 1422 |
| LMArena Korean | 1108 | 1428 |
| LMArena Russian | 1204 | 1459 |
| LMArena Spanish | 1165 | 1472 |
Instruction Following ERNIE 5.1 leads
Claude 3 Haiku: 61.5 (#242), ERNIE 5.1: 76.9 (#35)
| Benchmark | Claude 3 Haiku | ERNIE 5.1 |
|---|---|---|
| LMArena Instruction Following | 1174 | 1460 |
Long Context ERNIE 5.1 leads
Claude 3 Haiku: 36.1 (#232), ERNIE 5.1: 44.7 (#56)
| Benchmark | Claude 3 Haiku | ERNIE 5.1 |
|---|---|---|
| LMArena Longer Query | 1191 | 1462 |
Writing & Preference ERNIE 5.1 leads
Claude 3 Haiku: 29.8 (#286), ERNIE 5.1: 65.3 (#50)
| Benchmark | Claude 3 Haiku | ERNIE 5.1 |
|---|---|---|
| LMArena Text | 1195 | 1468 |
| LMArena Creative Writing | 1157 | 1440 |
| LMArena Multi-Turn | 1190 | 1471 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than ERNIE 5.1?
ERNIE 5.1 is the stronger model overall, scoring 43.1 to 25.7 on the Noometry Index.
Is Claude 3 Haiku or ERNIE 5.1 better for coding?
ERNIE 5.1 scores higher on coding benchmarks: 43.4 versus 26.1 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and ERNIE 5.1 share?
17 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and ERNIE 5.1 has 19.