Kimi K3 beats GLM 5.2 on 100 deep-research tasks, but costs 5x more
AravSrinivas · x · 2026-07-24
We benchmarked Kimi K3 and GLM 5.2 on 100 deep-research tasks from DRACO (via Perplexity) and had Fable judge the results.
- Kimi K3: 71.6 mean score, 77% pass rate
- GLM 5.2: 41.5 mean score, 22% pass rate
- Runtime / cost: K3 took 3h 38m and cost $60; GLM finished in 1h 45m for $12.50
The thread says K3 scored much higher, but GLM was substantially faster and cheaper. A full deep-dive thread is linked in the original post.
More from Models
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- DeepSeek V4 Pro API to continue after Sept 2026, billing unchanged — teortaxesTex · 2026-09-11
- DeepSeek V4.1 Flash Hits 98% of GPT-6 Astra's Score at 1.4% of the Cost in Third-Party Benchmark — ayushtweetshere · 2026-09-11
- TheZvi Polls: Has Your Coding Model Choice Changed Since Fable 5.1 and Astra? — TheZvi · 2026-09-11
- antirez Weighs In on Anthropic Banning Minors From Using Claude — antirez · 2026-09-11