Model comparison
ERNIE 5.0 0110 vs Mixtral 8x7B
ERNIE 5.0 0110 is the stronger model overall, scoring 41.8 to 27.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Baidu
Mistral AISummary
- They share 17 benchmarks with published results for both. ERNIE 5.0 0110 scores higher in 7 categories and Mixtral 8x7B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.0 0110 leads 63.1 to 34.2.
- Mixtral 8x7B has downloadable open weights; the other is API-only.
Side by side
| ERNIE 5.0 0110 | Mixtral 8x7B | |
|---|---|---|
| Provider | Baidu | Mistral AI |
| Noometry Index | 41.8 | 27.1 |
| Released | — | 2023-12-11 |
| Weights | Proprietary | Open |
| Context window | — | 32K |
| Max output | — | 32K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $0.70 |
| Results tracked | 20 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding ERNIE 5.0 0110 leads
ERNIE 5.0 0110: 43.0 (#94), Mixtral 8x7B: 32.8 (#269)
| Benchmark | ERNIE 5.0 0110 | Mixtral 8x7B |
|---|---|---|
| LMArena Coding | 1455 | 1126 |
| HumanEval+ | — | 39.6% |
| MBPP+ | — | 49.7% |
Reasoning Mixtral 8x7B leads
ERNIE 5.0 0110: 17.0 (#297), Mixtral 8x7B: 18.2 (#285)
| Benchmark | ERNIE 5.0 0110 | Mixtral 8x7B |
|---|---|---|
| LMArena Hard Prompts | 1445 | 1115 |
| NYT Connections (extended) | 10.3% | — |
| Thematic Generalization | 41.7% | — |
| DTBench | — | 49.6% |
| Adversarial NLI | — | 55.2% |
| Epoch Capabilities Index | — | 118.47 |
| ForecastBench | — | 56.3 |
| HellaSwag | — | 86.7% |
| PIQA | — | 83.6% |
| WinoGrande | — | 77.2% |
Math ERNIE 5.0 0110 leads
ERNIE 5.0 0110: 39.3 (#110), Mixtral 8x7B: 18.8 (#289)
| Benchmark | ERNIE 5.0 0110 | Mixtral 8x7B |
|---|---|---|
| LMArena Math | 1437 | 1147 |
| Omni-MATH | — | 10.5% |
| MATH Level 5 | — | 10% |
| GSM8K | — | 74.4% |
Knowledge ERNIE 5.0 0110 leads
ERNIE 5.0 0110: 39.8 (#128), Mixtral 8x7B: 11.0 (#301)
| Benchmark | ERNIE 5.0 0110 | Mixtral 8x7B |
|---|---|---|
| LMArena Expert | 1428 | 1088 |
| GPQA Diamond | — | 30.6% |
| MMLU-Pro | — | 33.5% |
| GPQA (HELM) | — | 29.6% |
| ARC (AI2) Challenge | — | 87.3% |
| MMLU | — | 70.6% |
| OpenBookQA | — | 85.8% |
| TriviaQA | — | 82.2% |
Multimodal Not comparable
ERNIE 5.0 0110: 39.9 (#53), Mixtral 8x7B: —
| Benchmark | ERNIE 5.0 0110 | Mixtral 8x7B |
|---|---|---|
| LMArena Vision | 1249 | — |
Multilingual ERNIE 5.0 0110 leads
ERNIE 5.0 0110: 54.1 (#49), Mixtral 8x7B: 29.6 (#266)
| Benchmark | ERNIE 5.0 0110 | Mixtral 8x7B |
|---|---|---|
| LMArena Non-English | 1436 | 1077 |
| LMArena Chinese | 1512 | 1055 |
| LMArena French | 1467 | 1166 |
| LMArena German | 1460 | 1114 |
| LMArena Japanese | 1382 | 931 |
| LMArena Korean | 1406 | 968 |
| LMArena Russian | 1446 | 1090 |
| LMArena Spanish | 1473 | 1111 |
Instruction Following ERNIE 5.0 0110 leads
ERNIE 5.0 0110: 74.5 (#92), Mixtral 8x7B: 51.0 (#297)
| Benchmark | ERNIE 5.0 0110 | Mixtral 8x7B |
|---|---|---|
| LMArena Instruction Following | 1413 | 1109 |
| IFEval | — | 57.5% |
Long Context ERNIE 5.0 0110 leads
ERNIE 5.0 0110: 43.4 (#95), Mixtral 8x7B: 33.4 (#260)
| Benchmark | ERNIE 5.0 0110 | Mixtral 8x7B |
|---|---|---|
| LMArena Longer Query | 1422 | 1103 |
Writing & Preference ERNIE 5.0 0110 leads
ERNIE 5.0 0110: 63.1 (#66), Mixtral 8x7B: 34.2 (#270)
| Benchmark | ERNIE 5.0 0110 | Mixtral 8x7B |
|---|---|---|
| LMArena Text | 1445 | 1132 |
| LMArena Creative Writing | 1426 | 1109 |
| LMArena Multi-Turn | 1434 | 1115 |
| WildBench | — | 67.3% |
Frequently asked questions
Is ERNIE 5.0 0110 better than Mixtral 8x7B?
ERNIE 5.0 0110 is the stronger model overall, scoring 41.8 to 27.1 on the Noometry Index.
Is ERNIE 5.0 0110 or Mixtral 8x7B better for coding?
ERNIE 5.0 0110 scores higher on coding benchmarks: 43.0 versus 32.8 in the Noometry coding category.
How many benchmarks do ERNIE 5.0 0110 and Mixtral 8x7B share?
17 benchmarks have published results for both models. ERNIE 5.0 0110 has 20 scored results on Noometry and Mixtral 8x7B has 38.