List your company

Mathematical Problem Solving on AIME 2025

100ScoreGPT-5.2
-3.79223.15450.177.046Dec 15, 2025Jan 9, 2026Feb 4, 2026Mar 2, 2026Mar 28, 2026Apr 23, 2026May 19, 2026

Evaluation results

MethodLinks
GPT-5.2Reasoning Effort=high2026.05100
STAR-PólyaMathBackbone=all GPT-5.5xh2026.05100
Claude Opus 4.7Reasoning Effort=xhigh2026.0598.33
GPT-5.4Reasoning Effort=xhigh2026.0597.5
GPT-5.5Reasoning Effort=xhigh2026.0596.67
Claude Opus 4.6Reasoning Effort=high2026.0596.67
DeepSeek-V3.2-Speciale2026.0596.04
GLM-5Precision=FP82026.0595.83
DeepSeek-v3.2-Speciale2026.0595.83
Kimi K2.5Reasoning Effort=Think2026.0595.83
Step-3.5-Flash2026.0595.73
GLM-4-72026.0595.42
Gemini 3 Pro2026.0595
GPT-5-2025-08-07Setting=high2026.0594.06
Kimi-K2Mode=Thinking2026.0594.06
Gemini-3-Pro-Preview2026.0593.44
gpt-oss-120bSetting=high2026.0593.44
Gemini 3.1 Pro2026.0593.33
DeepSeek-V3.22026.0593.02
Mimo-V2-Flash2026.0592.92
Kimi-K2.52026.0591.88
gpt-oss-120bNumber of Parameters=117B, Optimization Level=high2026.0191.7
o4-mini-2025-04-16Setting=high2026.0591.04
GPT-5-mini-2025-08-07Setting=high2026.0590.94
Qwen3Parameters=235B, Active Parameters=A22B, Mode=Thinking, Version=25072026.0590.94
GLM-4.62026.0590.31
Kimi K2.6Reasoning Effort=Think2026.0589.17
Qwen3-NextParameters=80B, Active Parameters=A3B, Mode=Thinking2026.0588.96
DeepSeek-R1-05282026.0588.96
Gemini-2.5-Pro2026.0588.65
gpt-oss-20bSetting=high2026.0587.92
Qwen3Parameters=30B, Active Parameters=A3B, Mode=Thinking, Version=25072026.0586.77
MiniMax-M2.52026.0586.25
Seed-OSS-36BType=Instruct2026.0586.04
GLM-4.52026.0585.83
GPT-5-nano-2025-08-07Setting=high2026.0585.42
o3-2025-04-162026.0585.1
GLM-4.5-Air2026.0584.79
Solar OpenNumber of Parameters=102B2026.0184.3
o3-mini-2025-04-16Setting=high2026.0583.85
doubao-seed-1.6Mode=thinking, Version=2506152026.0582.81
GLM-4.5-AirNumber of Parameters=110B2026.0182.7
Qwen3Parameters=235B, Active Parameters=A22B, Mode=Thinking2026.0582.4
MiniCPM-Sala2026.0581.04
Qwen3-4BMode=Thinking, Version=25072026.0580
MiniMax-M22026.0579.06
TeleChatMode=Thinking2026.0578.96
ERNIE-4.5Parameters=21B, Active Parameters=A3B, Mode=Thinking2026.0576.15
gpt-oss-120bNumber of Parameters=117B, Optimization Level=medium2026.0175
Finix-P1-32BMode=Thinking2026.0570.21
Qwen3Parameters=235B, Active Parameters=A22B, Type=Instruct, Version=25072026.0569.48
Qwen3-NextParameters=80B, Active Parameters=A3B, Type=Instruct2026.0569.17
QwQ-32B2026.0568.96
Claude Sonnet 4Mode=Thinking2026.0568.65
JTMode=Think2026.0565.94
Hunyuan-A13BType=Instruct2026.0565.73
Qwen3Parameters=30B, Active Parameters=A3B, Type=Instruct, Version=25072026.0563.75
GLM-Z1-32B-04142026.0561.15
LongCat-Flash-Chat2026.0561.04
Kimi-K2Type=Instruct2026.0549.06
Qwen3-4BType=Instruct, Version=25072026.0546.88
DeepSeek-Chat-V3-03242026.0545.1
Qwen 3 VL 8B Inststage=Instruct2025.1243.3
GPT-4.1-202504142026.0535.31
GLM-4-32B-04142026.0533.44
ERNIE-4.5Parameters=300B, Active Parameters=A47B, Type=PT2026.0532.6
Olmo 3 7B Instructstage=Final Instruct2025.1232.5
Gemma-3-27B-it2026.0522.4
Qwen 3 8Bstage=Instruct2025.1221.7
Olmo 3 7B Instructstage=DPO2025.1220.4
Llama4-MaverickParameters=17B, Experts=128E, Type=Instruct2026.0515.21
Olmo 3 7B Instructstage=SFT2025.127.2
Qwen 2.5 7Bstage=Instruct2025.126.3
Granite 3.3 8B Inststage=Instruct2025.126.3
OLMo 2 7B Inststage=Instruct2025.120.4
Apertus 8B Inststage=Instruct2025.120.2