← All comparisons
ERNIE 5.0 Thinking Preview vs Qwen3 4B 2507 Instruct
Baidu vs Alibaba — side-by-side benchmark comparison
| ERNIE 5.0 Thinking Preview | Qwen3 4B 2507 Instruct | |
|---|---|---|
| Intelligence Index | 29.1 | 12.9 |
| Coding Index | 29.2 | 9.0 |
| Math Index | 85.0 | 52.3 |
| Output speed (tok/s) | 0.0 | 0.0 |
| Blended price ($/1M) | $0.00 | $0.00 |
| Time to first token (s) | 0.00s | 0.00s |
| aime | — | — |
| aime 25 | 85.0% | 52.3% |
| artificial analysis coding index | 29.20 | 9.00 |
| artificial analysis intelligence index | 29.10 | 12.90 |
| artificial analysis math index | 85.00 | 52.30 |
| gpqa | 77.7% | 51.7% |
| hle | 12.7% | 4.7% |
| ifbench | 41.4% | 33.5% |
| lcr | 6.7% | 7.3% |
| livecodebench | 81.2% | 37.7% |
| math 500 | — | — |
| mmlu pro | 83.0% | 67.2% |
| scicode | 37.5% | 18.1% |
| tau2 | 83.9% | 26.6% |
| terminalbench hard | 25.0% | 4.5% |
Benchmark data from Artificial Analysis.