SOTA Mathematical Reasoning on IMO-AnswerBench and PapersWithCode

93.71Accuracy

Kimi-K2.6

Updated 16d ago

Evaluation Results

Method
Kimi-K2.6 2026.06	93.71	-
DS-v4-Pro 2026.06	93	-
Nemotron 3 Ultra 2026.06	92.3	-
GLM-5.1 2026.06	91.1	-
Kimi-K2.6 2026.06	91.1	-
DS-v4-Flash 2026.06	91.1	-
DS-v4-Flash 2026.06	89.6	-
Nemotron 3 Ultra 2026.06	88.6	-
GLM-5.1 2026.06	86.8	-
DS-v4-Pro 2026.06	85.4	-
Qwen-3.5 2026.06	84.51	-
DeepSeek-V3.2 2025.12	84.5	45
Gemini-3.0 2025.12	83.3	18
Gemini 3 Pro 2026.04	83.2	-
Gemini-3.0 2026.02	83.1	18,000
Qwen-3.5 2026.06	83.1	-
GLM-4.7 2026.07	82	-
Kimi K2.5 2026.02	81.8	36,000
Kimi K2 2026.02	78.6	37,000
Kimi-K2 2025.12	78.6	37
DeepSeek-V3.2 2026.02	78.3	27,000
DeepSeek-V3.2 2025.12	78.3	27
QED-Nano (+ RSA test-time scaffold) 2026.04	76.5	-
GPT-5 2025.12	76	31
GPT-5 High 2026.07	76	-
DeepSeek-Math-V2 2026.04	75.8	-
MiniMax-2.7 2026.06	75.1	-
Qwen3-30B-A3B SAO 2026.07	74	-
Qwen3-30B-A3B - SAO (w/ DIS only) 2026.07	71.3	-
Qwen3-235B-A22B-Thinking-2507 2026.04	70.5	-
GPT-OSS-120B 2026.04	70.5	-
Qwen3-30B-A3B - GRPO (+ DIS) 2026.07	70	-
MiniMax-2.7 2026.06	68.3	-
QED-Nano 2026.04	67.5	-
Qwen3-30B-A3B-Thinking-2507 2026.04	67	-
Claude-Sonnet-4.5 2026.07	65.8	-
GPT-OSS-20B 2026.04	61.5	-
QED-Nano (SFT initialization only) 2026.04	57.5	-
Qwen3-4B-Thinking-2507 2026.04	55.8	-
Qwen3-30B-A3B GRPO (w/ python) 2026.07	55.8	-
Qwen3-30B-A3B w/o python 2026.07	55.3	-
Qwen3-30B-A3B SFT (w/ python) 2026.07	53.3	-
Nomos-1 2026.04	49	-
Qwen3-30B-A3B SFT (w/o python) 2026.07	42	-
Qwen3-30B-A3B w/ python 2026.07	7.8	-