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

Reasoning on ARC

94.5Accuracy

Qwen-7B-Instruct

Updated 1mo ago

Evaluation Results

Method
Qwen-7B-Instruct 2025.10	94.5	-	-	-	-	112	-
Qwen-7B-Instruct 2025.10	94.5	-	-	-	-	111.8	-
Qwen3-8B 2026.02	92.34	-	-	-	-	-	-
Qwen3-8B 2026.02	91.98	-	-	-	-	-	-
Qwen3-4B 2026.02	90.84	-	-	-	-	-	-
HARP-E 2026.06	90.8	-	-	-	-	-	-
Qwen3-4B 2026.02	89.98	-	-	-	-	-	-
LLaMA-8B-Instruct 2025.10	89.4	-	-	-	-	104	-
FL 2026.04	89	-	-	-	-	-	-
GEM 2026.04	88.9	-	-	-	-	-	-
CE 2026.04	88.7	-	-	-	-	-	-
TOFU 2026.04	88.7	-	-	-	-	-	-
LLaMA-8B-Instruct 2025.10	88.5	-	-	-	-	106.9	-
PPCV 2026.02	88.31	-	-	-	-	-	-
FL 2026.04	88.3	-	-	-	-	-	-
TOFU 2026.04	88.2	-	-	-	-	-	-
CE 2026.04	88.1	-	-	-	-	-	-
GEM 2026.04	87.9	-	-	-	-	-	-
SFT+GRPO 2026.06	87.8	-	-	-	-	-	405
ADaPTthink 2026.06	87.7	-	-	-	-	-	327
FDM-A 2025.12	87.66	-	38.43	-	-	-	-
GEM 2026.04	87	-	-	-	-	-	-
CE 2026.04	86.9	-	-	-	-	-	-
FL 2026.04	86.9	-	-	-	-	-	-
TOFU 2026.04	86.9	-	-	-	-	-	-
ADaPT 2026.06	86.9	-	-	-	-	-	78
λ-PR 2026.04	86.7	-	-	-	-	-	-
ARM 2026.06	86.7	-	-	-	-	-	204
Probability 2025.12	86.38	-	21.71	-	-	-	-
FDM-A 2025.12	86.3	-	38.2	-	-	-	-
GEM 2026.04	86.2	-	-	-	-	-	-
CE 2026.04	86.1	-	-	-	-	-	-
λ-PR 2026.04	86.1	-	-	-	-	-	-
Margin 2025.12	85.91	-	21.34	-	-	-	-
TOFU 2026.04	85.8	-	-	-	-	-	-
FL 2026.04	85.7	-	-	-	-	-	-
HARP-C 2026.06	85.7	-	-	-	-	-	-
EB 2025.12	85.68	-	34.89	-	-	-	-
AdaPreLoRA AdamW 2026.05	85.6	-	-	-	-	-	-
Phi-Decoding 2026.02	85.41	-	-	-	-	-	-
WINO 2025.12	85.31	-	35.27	-	-	-	-
Scaled AdamW 2026.05	85.3	-	-	-	-	-	-
ADaPTanswer 2026.06	85.3	-	-	-	-	-	42
R-4B 2026.06	84.7	-	-	-	-	-	274
Entropy 2025.12	84.58	-	20.48	-	-	-	-
Predictive Decoding 2026.02	84.56	-	-	-	-	-	-
Margin 2025.12	84.34	-	20.65	-	-	-	-
AdamW 2026.05	84.3	-	-	-	-	-	-
CES 2026.05	83.6	-	-	-	-	-	542
FDM-A 2025.12	83.33	-	12.62	-	-	-	-
TLMRE 2026.06	82.6	-	-	-	-	-	287
Probability 2025.12	82.16	-	21.24	-	-	-	-
SHED-O 2026.06	81.9	-	-	-	-	-	-
Guided Decoding 2026.02	81.74	-	-	-	-	-	-
LoRA-Pro AdamW 2026.05	80.9	-	-	-	-	-	-
SOAP 2026.05	80.9	-	-	-	-	-	-
Tree-of-Thought 2026.02	80.72	-	-	-	-	-	-
LLaMA3.1-8B 2026.02	80.6	-	-	-	-	-	-
LLaMA3.1-8B 2026.02	80.41	-	-	-	-	-	-
DAPO 2026.05	79.7	-	-	-	-	-	543
WINO 2025.12	79.44	-	34.17	-	-	-	-
λ-PR 2026.04	78.8	-	-	-	-	-	-
GEM 2026.04	77.3	-	-	-	-	-	-
Entropy 2025.12	77.2	-	19.91	-	-	-	-
λ-PR 2026.04	77.2	-	-	-	-	-	-
FL 2026.04	76.8	-	-	-	-	-	-
GEM 2026.04	76.8	-	-	-	-	-	-
CE 2026.04	76.3	-	-	-	-	-	-
TOFU 2026.04	76.1	-	-	-	-	-	-
Margin 2025.12	75.48	-	8.56	-	-	-	-
CE 2026.04	74.6	-	-	-	-	-	-
TOFU 2026.04	74.6	-	-	-	-	-	-
LLaMA-3B-Instruct 2025.10	74.5	-	-	-	-	99.5	-
CE 2026.04	74.4	-	-	-	-	-	-
FL 2026.04	74.3	-	-	-	-	-	-
GEM 2026.04	74.2	-	-	-	-	-	-
GEM 2026.04	74.1	-	-	-	-	-	-
TOFU 2026.04	74.1	-	-	-	-	-	-
FL 2026.04	74	-	-	-	-	-	-
HARP-C 2026.06	74	-	-	-	-	-	-
HARP-E 2026.06	74	-	-	-	-	-	-
TOFU 2026.04	73.9	-	-	-	-	-	-
FL 2026.04	73.7	-	-	-	-	-	-
EB 2025.12	73.55	-	32.01	-	-	-	-
CE 2026.04	73.5	-	-	-	-	-	-
LLaMA-3B-Instruct 2025.10	73.5	-	-	-	-	103.9	-
SFT 2026.06	73.2	-	-	-	-	-	949
Probability 2025.12	72.74	-	8.68	-	-	-	-
TOFU 2026.04	72.5	-	-	-	-	-	-
TOFU 2026.04	72.3	-	-	-	-	-	-
GEM 2026.04	72.1	-	-	-	-	-	-
SFT+GRPO 2026.06	72.1	-	-	-	-	-	577
CE 2026.04	71.8	-	-	-	-	-	-
GEM 2026.04	71.8	-	-	-	-	-	-
Apertus-8B 2026.05	71.66	-	-	-	-	-	-
EB 2025.12	71.5	-	8.98	-	-	-	-
ADaPT 2026.06	71.5	-	-	-	-	-	74
CE 2026.04	71.4	-	-	-	-	-	-
FL 2026.04	71.2	-	-	-	-	-	-
FL 2026.04	71.1	-	-	-	-	-	-

Showing 100 of 282 rows