News

BenchLM
benchlm.ai > compare > gpt-5-5-vs-qwen3-6-27b

GPT-5.5 vs Qwen3.6-27B: Benchmarks, Pricing, Speed (July 2026)

11+ hour, 36+ min ago  (548+ words) Head-to-head evidence from 24 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane. Evidence parity. GPT-5.5 and Qwen3.6-27B share 24 comparable benchmark results. 5 of 8 categories are comparable. 33 results are unique to GPT-5.5; 31 to Qwen3.6-27B. Pick GPT-5.5 if you…...

BenchLM
benchlm.ai > compare > kimi-2-6-vs-qwen3-7-plus

Kimi K2.6 vs Qwen3.7 Plus: Benchmarks, Pricing, Speed (July 2026)

11+ hour, 36+ min ago  (537+ words) Head-to-head evidence from 36 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane. Verified leaderboard positions: Kimi K2.6 #11; Qwen3.7 Plus #4 BenchAlign evidence: Kimi K2.6 estimated; Qwen3.7 Plus supported. Intervals and evidence labels describe ranking uncertainty, not a guarantee for…...

BenchLM
benchlm.ai > compare > gpt-5-6-terra-vs-soofi-s-30b-a3b

GPT-5.6 Terra vs Soofi S 30B-A3B: Benchmarks, Pricing, Speed (July 2026)

1+ day, 11+ hour ago  (387+ words) Head-to-head evidence from 2 shared benchmark results across 1 category. Overall scores shown here use the public BenchAlign v5 ranking lane. BenchAlign evidence: GPT-5.6 Terra estimated; Soofi S 30B-A3B not scored. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific…...

BenchLM
benchlm.ai > compare > gpt-5-6-luna-vs-soofi-s-30b-a3b

GPT-5.6 Luna vs Soofi S 30B-A3B: Benchmarks, Pricing, Speed (July 2026)

1+ day, 11+ hour ago  (387+ words) Head-to-head evidence from 2 shared benchmark results across 1 category. Overall scores shown here use the public BenchAlign v5 ranking lane. BenchAlign evidence: GPT-5.6 Luna estimated; Soofi S 30B-A3B not scored. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific…...

BenchLM
benchlm.ai > blog > posts > thinking-machines-chose-open-weights-first

Thinking Machines Chose Open Weights First

1+ day, 11+ hour ago  (1707+ words) Why Thinking Machines made its first foundation-model release open weight, what Inkling changes for the lab, and where it falls short of the closed frontier. Seventeen months after Thinking Machines Lab publicly introduced itself, the company released its first foundation…...

BenchLM
benchlm.ai > compare > gpt-5-4-vs-soofi-s-30b-a3b

GPT-5.4 vs Soofi S 30B-A3B: Benchmarks, Pricing, Speed (July 2026)

1+ day, 7+ hour ago  (390+ words) Head-to-head evidence from 2 shared benchmark results across 1 category. Overall scores shown here use the public BenchAlign v5 ranking lane. Verified leaderboard positions: GPT-5.4 #10; Soofi S 30B-A3B unranked BenchAlign evidence: GPT-5.4 supported; Soofi S 30B-A3B not scored. Intervals and evidence labels describe ranking uncertainty,…...

BenchLM
benchlm.ai > compare > gpt-5-6-sol-vs-soofi-s-30b-a3b

GPT-5.6 Sol vs Soofi S 30B-A3B: Benchmarks, Pricing, Speed (July 2026)

1+ day, 11+ hour ago  (387+ words) Head-to-head evidence from 2 shared benchmark results across 1 category. Overall scores shown here use the public BenchAlign v5 ranking lane. BenchAlign evidence: GPT-5.6 Sol estimated; Soofi S 30B-A3B not scored. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific…...

BenchLM
benchlm.ai > compare > gpt-5-4-vs-minimax-m3

GPT-5.4 vs MiniMax M3: Benchmarks, Pricing, Speed (July 2026)

1+ day, 11+ hour ago  (491+ words) Head-to-head evidence from 27 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane. Verified leaderboard positions: GPT-5.4 #10; MiniMax M3 #18 BenchAlign evidence: GPT-5.4 supported; MiniMax M3 supported. Intervals and evidence labels describe ranking uncertainty, not a guarantee for…...

BenchLM
benchlm.ai > compare > gpt-5-4-mini-vs-soofi-s-30b-a3b

GPT-5.4 mini vs Soofi S 30B-A3B: Benchmarks, Pricing, Speed (July 2026)

1+ day, 7+ hour ago  (323+ 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. GPT-5.4 mini and Soofi S 30B-A3B share 1 comparable benchmark result. 1 of 8 categories are comparable. 30 results are unique to GPT-5.4 mini; 7 to Soofi…...

BenchLM
benchlm.ai > compare > gpt-5-4-mini-vs-kimi-3

GPT-5.4 mini vs Kimi 3: Benchmarks, Pricing, Speed (July 2026)

1+ day, 11+ hour 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 mini and Kimi 3 share 0 comparable benchmark results. 0 of 8 categories are comparable. 31 results are unique to GPT-5.4 mini; 0 to Kimi 3. Benchmark…...