Qwen3.8-27B Open Weights Beat Claude Opus on SWE-bench Pro, 262K Context, $0.40/M Input
markjeffrey · x · 2026-08-18
Qwen shipped Qwen3.8-27B weights on Friday: dense 27B, Apache 2.0, 262K context, text + image input—and half of ML Twitter spent the weekend benchmarking it.
Published scores are striking: 61.7 on SWE-bench Pro (vs Claude Opus 4.6 Max at 53.4), 90.3 on LiveCodeBench v6 (88.8), 84.3 on OSWorld-Verified (72.7), and 89.2 on GPQA Diamond, beating Claude's flagship on several benchmarks.
It's already live on Chutes at $0.40/M input and $3.00/M output tokens, served inside a hardware-attested TEE with end-to-end encryption.
More from Models
- Meta open-sources Muse Spark Open agent model with day-0 TPU support in SGLang — BanghuaZ · 2026-10-16
- Saying "load-bearing" in your prompt makes Opus 5.5 stop holding back — zacharynado · 2026-10-16
- Americans get their Claude accounts banned while on business trips in China — dotey · 2026-10-16
- I priced every Grok Bot call: $20 to $200 plan in 5 days, long jobs eat 52% — jonathanmalkin · 2026-10-16
- NVIDIA releases Nemotron-3.5-Embed-1B, a multimodal embedding model covering 34 languages — jacek2023 · 2026-10-16
- EpochAI pegs GPT-6 training at up to 1.8e27 FLOP; scaling01 calls param estimates way too high — scaling01 · 2026-10-16