List your company

Reward Modeling on RewardBench Math 2

35.7AccuracyPointwise Rating
0.0289.28918.5527.811Feb 14, 2026

Evaluation results

MethodLinks
Pointwise RatingModel Family=QWEN3, Model Size=4B2026.0235.7
Pointwise RatingModel Family=QWEN3, Model Size=8B2026.0235.7
Listwise Ranking*Model Family=GEMMA3, Model Size=4B2026.0231.8
FLIPModel Family=QWEN3, Model Size=8B2026.0231
Listwise Ranking*Model Family=MISTRAL, Model Size=7B2026.0230.3
Pointwise RatingModel Family=QWEN3, Model Size=1.7B2026.0230.2
FLIPModel Family=QWEN3, Model Size=1.7B2026.0230.2
Pairwise Ranking*Model Family=GEMMA3, Model Size=4B2026.0230.2
Listwise Ranking*Model Family=LLAMA3, Model Size=8B2026.0229.8
FLIPModel Family=MISTRAL, Model Size=7B2026.0229.7
FLIPModel Family=QWEN3, Model Size=4B2026.0229.4
Pairwise Ranking*Model Family=LLAMA3, Model Size=8B2026.0229.3
FLIPModel Family=OLMO2, Model Size=1B2026.0228.4
Listwise Ranking*Model Family=QWEN3, Model Size=1.7B2026.0227.2
FLIPModel Family=GEMMA3, Model Size=4B2026.0227.1
Pairwise Ranking*Model Family=MISTRAL, Model Size=7B2026.0226.8
FLIPModel Family=LLAMA3, Model Size=1B2026.0226.6
FLIPModel Family=OLMO2, Model Size=7B2026.0226.3
FLIPModel Family=QWEN3, Model Size=0.6B2026.0226.3
FLIPModel Family=GEMMA3, Model Size=1B2026.0226.2
FLIPModel Family=LLAMA3, Model Size=8B2026.0225.8
Listwise Ranking*Model Family=OLMO2, Model Size=1B2026.0224
FLIPModel Family=LLAMA3, Model Size=3B2026.0223.8
Pairwise Ranking*Model Family=QWEN3, Model Size=1.7B2026.0223.1
Listwise Ranking*Model Family=GEMMA3, Model Size=1B2026.0222.8
Pairwise Ranking*Model Family=OLMO2, Model Size=7B2026.0222.7
Listwise Ranking*Model Family=LLAMA3, Model Size=3B2026.0222.7
Pairwise Ranking*Model Family=GEMMA3, Model Size=1B2026.0222.5
FLIPModel Family=GEMMA3, Model Size=270M2026.0222.4
Pointwise RatingModel Family=GEMMA3, Model Size=4B2026.0222.1
Pointwise RatingModel Family=LLAMA3, Model Size=8B2026.0221.4
Pointwise RatingModel Family=QWEN3, Model Size=0.6B2026.0221.1
Pointwise RatingModel Family=LLAMA3, Model Size=3B2026.0220.3
Pointwise RatingModel Family=LLAMA3, Model Size=1B2026.0219.9
Listwise Ranking*Model Family=OLMO2, Model Size=7B2026.0219
Pairwise Ranking*Model Family=LLAMA3, Model Size=3B2026.0218.7
Pointwise RatingModel Family=GEMMA3, Model Size=270M2026.0218.7
Listwise Ranking*Model Family=LLAMA3, Model Size=1B2026.0217.6
Pointwise RatingModel Family=GEMMA3, Model Size=1B2026.0216.9
Pairwise Ranking*Model Family=QWEN3, Model Size=4B2026.0216
Pointwise RatingModel Family=OLMO2, Model Size=7B2026.0213.2
Pairwise Ranking*Model Family=QWEN3, Model Size=8B2026.0212.9
Listwise Ranking*Model Family=GEMMA3, Model Size=270M2026.0211.6
Pointwise RatingModel Family=OLMO2, Model Size=1B2026.0210.3
Pointwise RatingModel Family=MISTRAL, Model Size=7B2026.0210.1
Pairwise Ranking*Model Family=LLAMA3, Model Size=1B2026.029.7
Pairwise Ranking*Model Family=QWEN3, Model Size=0.6B2026.028.2
Pairwise Ranking*Model Family=GEMMA3, Model Size=270M2026.025.9
Listwise Ranking*Model Family=QWEN3, Model Size=0.6B2026.024.5
Listwise Ranking*Model Family=QWEN3, Model Size=8B2026.023.6
Listwise Ranking*Model Family=QWEN3, Model Size=4B2026.023.2
Pairwise Ranking*Model Family=OLMO2, Model Size=1B2026.021.4