Our new X account is live! Follow @wizwand_team for updates

Process-outcome alignment on PRIME Chemistry

93.35Outcome Score

DeepSeek-V3.2-thinking

Updated 4d ago

Evaluation Results

Method	Links
DeepSeek-V3.2-thinking 2026.02		93.35	88.49
Kimi-K2-thinking 2026.02		92.46	89
Claude-Sonnet-4.5-thinking 2026.02		92.2	88.11
Grok-4-thinking 2026.02		91.82	89
Claude-Opus-4-thinking 2026.02		91.43	86.57
Qwen3-4B-thinking-2507 2026.02		91.3	83.76
GPT-5.2-chat 2026.02		91.3	86.45
Gemini-2.5-Pro-thinking 2026.02		91.3	90.15
GPT-5.2-thinking 2026.02		91.3	88.49
Claude-Sonnet-4-thinking 2026.02		90.28	85.29
GPT-OSS-120B 2026.02		90.03	79.8
GPT-5-thinking 2026.02		89.64	88.62
Claude-Opus-4 2026.02		89.26	80.43
Gemini-3.0-pro-thinking 2026.02		89.26	86.19
Claude-Opus-4.5 2026.02		89.13	79.67
Seed-1.6-thinking 2026.02		89.13	79.8
CompassVerifier-32B 2026.02		89.13	73.66
GLM-4.6 2026.02		89	84.91
Claude-Sonnet-4 2026.02		88.62	77.75
Claude-Sonnet-4.5 2026.02		88.36	77.49
DeepSeek-V3.2 2026.02		88.24	77.62
Qwen3-30B-A3B 2026.02		88.24	83.38
GPT-OSS-20B 2026.02		88.24	79.8
SCI-Verifier-4B 2026.02		87.98	73.53
Claude-Opus-4.5-thinking 2026.02		87.85	81.84
Qwen3-8B 2026.02		87.47	77.37
Qwen3-4B 2026.02		86.57	75.83
Tencent-Qwen2.5-7B-RLVR 2026.02		84.65	71.23
xVerify-9B-C 2026.02		83.89	72.55
GPT-5-chat 2026.02		82.74	68.67
Qwen3-4B-Instruct-2507 2026.02		80.05	70.2
Phi-4 2026.02		80.05	63.81
General-Verifier 2026.02		77.49	63.04
Math-Verify 2026.02		69.69	65.47