← All comparisons
EXAONE 4.5 33B (Non-reasoning) vs Qwen3.6 35B A3B (Reasoning)
LG AI Research vs Alibaba — side-by-side benchmark comparison
| EXAONE 4.5 33B (Non-reasoning) | Qwen3.6 35B A3B (Reasoning) | |
|---|---|---|
| Intelligence Index | — | 43.5 |
| Coding Index | — | 35.2 |
| Math Index | — | — |
| Output speed (tok/s) | 0.0 | 159.1 |
| Blended price ($/1M) | $0.00 | $0.56 |
| Time to first token (s) | 0.00s | 1.50s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | — | 35.20 |
| artificial analysis intelligence index | — | 43.50 |
| artificial analysis math index | — | — |
| gpqa | — | 84.1% |
| hle | — | 20.2% |
| ifbench | — | 64.4% |
| lcr | — | 63.7% |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | — | 35.8% |
| tau2 | — | 95.3% |
| terminalbench hard | — | 34.8% |
Benchmark data from Artificial Analysis.