← All comparisons
ERNIE 4.5 300B A47B vs Claude 4.1 Opus (Reasoning)
Baidu vs Anthropic — side-by-side benchmark comparison
| ERNIE 4.5 300B A47B | Claude 4.1 Opus (Reasoning) | |
|---|---|---|
| Intelligence Index | 15.0 | 42.0 |
| Coding Index | 14.5 | 36.5 |
| Math Index | 41.3 | 80.3 |
| Output speed (tok/s) | 25.7 | 44.5 |
| Blended price ($/1M) | $0.48 | $32.81 |
| Time to first token (s) | 1.68s | 8.55s |
| aime | 49.3% | — |
| aime 25 | 41.3% | 80.3% |
| artificial analysis coding index | 14.50 | 36.50 |
| artificial analysis intelligence index | 15.00 | 42.00 |
| artificial analysis math index | 41.30 | 80.30 |
| gpqa | 81.1% | 80.9% |
| hle | 3.5% | 11.9% |
| ifbench | 39.1% | 55.4% |
| lcr | 2.3% | 66.3% |
| livecodebench | 46.7% | 65.4% |
| math 500 | 93.1% | — |
| mmlu pro | 77.6% | 88.0% |
| scicode | 31.5% | 40.9% |
| tau2 | 0.0% | 71.4% |
| terminalbench hard | 6.1% | 34.3% |
Benchmark data from Artificial Analysis.