List your company

Reward Modeling on RewardBench Average 2

39.7AccuracyFLIP
0.1810.4420.730.96Feb 14, 2026

Evaluation results

MethodLinks
FLIPModel Family=QWEN3, Model Size=8B2026.0239.7
FLIPModel Family=QWEN3, Model Size=4B2026.0238.1
FLIPModel Family=MISTRAL, Model Size=7B2026.0237.3
FLIPModel Family=QWEN3, Model Size=0.6B2026.0236.3
FLIPModel Family=GEMMA3, Model Size=4B2026.0235.7
FLIPModel Family=QWEN3, Model Size=1.7B2026.0235.5
FLIPModel Family=OLMO2, Model Size=7B2026.0235.3
FLIPModel Family=LLAMA3, Model Size=8B2026.0235.1
FLIPModel Family=OLMO2, Model Size=1B2026.0233.1
FLIPModel Family=GEMMA3, Model Size=1B2026.0233.1
Pointwise RatingModel Family=QWEN3, Model Size=8B2026.0232.2
FLIPModel Family=GEMMA3, Model Size=270M2026.0231.2
Listwise Ranking*Model Family=MISTRAL, Model Size=7B2026.0230.6
Listwise Ranking*Model Family=GEMMA3, Model Size=4B2026.0230
Pointwise RatingModel Family=QWEN3, Model Size=4B2026.0229.9
FLIPModel Family=LLAMA3, Model Size=1B2026.0229.8
Listwise Ranking*Model Family=LLAMA3, Model Size=8B2026.0229.1
Pairwise Ranking*Model Family=GEMMA3, Model Size=4B2026.0228.3
FLIPModel Family=LLAMA3, Model Size=3B2026.0228.2
Pairwise Ranking*Model Family=MISTRAL, Model Size=7B2026.0227.3
Pairwise Ranking*Model Family=QWEN3, Model Size=4B2026.0226.9
Pairwise Ranking*Model Family=QWEN3, Model Size=1.7B2026.0225.9
Pairwise Ranking*Model Family=OLMO2, Model Size=7B2026.0224.8
Pairwise Ranking*Model Family=QWEN3, Model Size=8B2026.0224.8
Pointwise RatingModel Family=QWEN3, Model Size=1.7B2026.0224
Listwise Ranking*Model Family=QWEN3, Model Size=1.7B2026.0224
Pairwise Ranking*Model Family=LLAMA3, Model Size=8B2026.0223.2
Pairwise Ranking*Model Family=GEMMA3, Model Size=1B2026.0222.8
Listwise Ranking*Model Family=OLMO2, Model Size=7B2026.0222.1
Listwise Ranking*Model Family=GEMMA3, Model Size=1B2026.0221.9
Listwise Ranking*Model Family=LLAMA3, Model Size=3B2026.0221.1
Listwise Ranking*Model Family=OLMO2, Model Size=1B2026.0219.3
Pointwise RatingModel Family=GEMMA3, Model Size=4B2026.0217.7
Pointwise RatingModel Family=LLAMA3, Model Size=1B2026.0216.5
Pointwise RatingModel Family=GEMMA3, Model Size=270M2026.0216.5
Pointwise RatingModel Family=QWEN3, Model Size=0.6B2026.0216.2
Pairwise Ranking*Model Family=LLAMA3, Model Size=3B2026.0215.7
Listwise Ranking*Model Family=LLAMA3, Model Size=1B2026.0215.5
Pointwise RatingModel Family=LLAMA3, Model Size=8B2026.0215.5
Listwise Ranking*Model Family=QWEN3, Model Size=8B2026.0215.3
Listwise Ranking*Model Family=QWEN3, Model Size=0.6B2026.0215
Listwise Ranking*Model Family=QWEN3, Model Size=4B2026.0214.9
Pointwise RatingModel Family=LLAMA3, Model Size=3B2026.0213.9
Listwise Ranking*Model Family=GEMMA3, Model Size=270M2026.0213.8
Pairwise Ranking*Model Family=QWEN3, Model Size=0.6B2026.0213.7
Pointwise RatingModel Family=GEMMA3, Model Size=1B2026.0213.3
Pointwise RatingModel Family=OLMO2, Model Size=1B2026.0213.1
Pairwise Ranking*Model Family=GEMMA3, Model Size=270M2026.0211.1
Pairwise Ranking*Model Family=LLAMA3, Model Size=1B2026.0210.3
Pointwise RatingModel Family=OLMO2, Model Size=7B2026.028.9
Pointwise RatingModel Family=MISTRAL, Model Size=7B2026.027.9
Pairwise Ranking*Model Family=OLMO2, Model Size=1B2026.021.7