16+ hour, 44+ min ago  (303+ words) Head-to-head evidence from 0 shared benchmark results across 0 categories. Overall scores shown here use BenchLM's provisional ranking lane. Evidence parity. GPT-5.4 nano and Kimi 3 share 0 comparable benchmark results. 0 of 8 categories are comparable. 30 results are unique to GPT-5.4 nano; 0 to Kimi 3. Benchmark…...

1+ day, 16+ hour ago  (321+ words) Head-to-head evidence from 19 shared benchmark results across 6 categories. Overall scores shown here use BenchLM's provisional ranking lane. Verified leaderboard positions: Kimi K2.6 #13; Kimi K2.7 Code unranked Evidence parity. Kimi K2.6 and Kimi K2.7 Code share 19 comparable benchmark results. 0 of 8 categories are comparable. 41 results are…...

1+ day, 12+ hour ago  (361+ words) Head-to-head evidence from 20 shared benchmark results across 6 categories. Overall scores shown here use BenchLM's provisional ranking lane. Verified leaderboard positions: GPT-5.5 #6; Kimi K2.7 Code unranked Evidence parity. GPT-5.5 and Kimi K2.7 Code share 20 comparable benchmark results. 0 of 8 categories are comparable. 37 results are…...

1+ day, 12+ hour ago  (415+ words) Head-to-head evidence from 24 shared benchmark results across 6 categories. Overall scores shown here use BenchLM's provisional ranking lane. Evidence parity. GPT-5.4 and MiMo-V2.5-Pro share 24 comparable benchmark results. 3 of 8 categories are comparable. 30 results are unique to GPT-5.4; 6 to MiMo-V2.5-Pro. Pick…...

1+ day, 16+ hour ago  (285+ words) BenchLM mirrors the published score view for CursorBench. Claude Fable 5 leads the public snapshot at 70.5%, followed by GPT-5.6 Sol (67.2%) and Grok 4.5 (66.7%). BenchLM does not use these results to rank models overall. The published CursorBench snapshot is tightly clustered at the…...

3+ day, 16+ hour ago  (353+ words) Head-to-head evidence from 2 shared benchmark results across 1 category. Overall scores shown here use BenchLM's provisional ranking lane. Evidence parity. Claude Haiku 4.5 and GPT-5.4 mini share 2 comparable benchmark results. 1 of 8 categories are comparable. 3 results are unique to Claude Haiku 4.5; 29 to GPT…...

3+ day, 16+ hour ago  (370+ words) Head-to-head evidence from 1 shared benchmark result across 1 category. Overall scores shown here use BenchLM's provisional ranking lane. Evidence parity. Composer 2.5 and GPT-5.4 mini share 1 comparable benchmark result. 1 of 8 categories are comparable. 4 results are unique to Composer 2.5; 30 to GPT-5.4 mini. Pick…...

3+ day, 16+ hour ago  (383+ words) Head-to-head evidence from 1 shared benchmark result across 1 category. Overall scores shown here use BenchLM's provisional ranking lane. Evidence parity. Composer 2.5 and GPT-5.4 share 1 comparable benchmark result. 1 of 8 categories are comparable. 4 results are unique to Composer 2.5; 53 to GPT-5.4. Pick GPT-5.4 if…...

3+ day, 12+ hour ago  (340+ words) Head-to-head evidence from 20 shared benchmark results across 6 categories. Overall scores shown here use BenchLM's provisional ranking lane. Evidence parity. GPT-5.4 and GPT-OSS 120B share 20 comparable benchmark results. 0 of 8 categories are comparable. 34 results are unique to GPT-5.4; 8 to GPT-OSS 120B. Benchmark data for…...

2+ mon, 3+ day ago  (153+ words) BenchLM mirrors the published score view for HumanEval. DeepSeek V4 Pro Base leads the public snapshot at 76.8%, followed by DeepSeek V4 Flash Base (69.5%). BenchLM does not use these results to rank models overall. DeepSeek V4 Pro Base DeepSeek V4 Flash Base BenchLM uses freshness…...