Share your thoughts, 1 month free Claude Pro on usSee more

General Reasoning on MMLU Pro, Super GPQA, GPQA Diamond, and BBEH Suite

84MMLU Pro

DeepSeek-R1

Updated 1mo ago

Evaluation Results

Method
DeepSeek-R1 2026.03	84	59.9	71.5	34.9	-	62.6
GPT-4o 2026.03	74.6	46.3	50	22.3	-	48.3
Webinstruct-V (SFT only) 2026.03	68.6	38.4	46.8	13.5	-	41.8
Webinstruct-V (SFT then selected SFT) 2026.03	68.6	38.2	45.6	13	-	41.4
Webinstruct-V (SFT then random RL) 2026.03	68.6	39.4	47.8	15.8	-	42.9
Webinstruct-V (SFT easy + RL hard) 2026.03	68.4	40.2	50	16.7	-	43.8
General-Reasoner 2026.01	65.1	35.3	42.9	10.8	38.5	56
General-Reasoner 2026.01	62.8	32.5	42.9	12.2	37.6	54.3
R-Few (1%) 2026.01	62.8	32.7	40.4	11.8	36.9	55.1
Webinstruct-V (RL only) 2026.03	62.8	32.5	42.9	12.2	-	37.6
Absolute Zero 2026.01	62.5	33.5	36.8	10.8	35.9	52.8
DARC 2026.01	62.3	32.8	44.4	11.8	37.8	56.3
R-Zero 2026.01	61.6	31.8	40.5	11.3	36.3	53.7
SPICE 2026.01	61	32.4	40.4	12.1	36.5	53.9
Webscale (SFT only) 2026.03	60.7	37.3	39.2	13.4	-	37.7
Webscale (SFT easy + RL hard) 2026.03	60.3	38.8	43.7	15.7	-	39.6
Open-Reasoner-Zero 2026.03	59.4	32.8	36.6	12.2	-	35.3
Base Model 2026.01	58	30.4	33.3	10.5	33.1	49.9
Qwen2.5-7B-Instruct 2026.03	57	30.7	33.8	12.2	-	33.4
DARC 2026.01	56.9	29.2	38.9	11.2	34.1	52.2
SPICE 2026.01	56.5	28.3	37.9	11.3	33.5	50.2
R-Few (1%) 2026.01	55.9	29.4	35.4	11.2	33	49.9
Webscale (RL only) 2026.03	55.4	30.9	34	10.1	-	32.6
R-Zero 2026.01	54.2	27.8	36.4	10.4	32.2	48.2
Absolute Zero 2026.01	52.6	27.1	35.3	8.3	30.8	46.9
QwQ-32B 2026.03	52	43.6	54.5	22.6	-	43.2
Base Model 2026.01	51.6	25.4	26.3	8.1	27.9	41.9
Qwen3-4B-Base 2026.03	51.6	25.4	26.5	8.1	-	27.9
SimpleRL-Qwen2.5-7B-Zoo 2026.03	51.5	29.9	24.2	11.9	-	29.4
Qwen2.5-7B-Base 2026.03	47.7	26.7	29.3	8	-	27.9
DARC 2026.01	43.8	22.3	32.3	10.8	27.3	40.6
SPICE 2026.01	41.3	19.9	29.8	7.2	24.5	38.4
R-Zero 2026.01	37.4	17.9	21.7	7.8	21.2	35.2
Absolute Zero 2026.01	31.4	18.8	27.8	5	20.8	35.5
Base Model 2026.01	14.7	11.4	15.7	0.6	10.6	24.6