Skip to content

5 releases, +0.3%: open-weight coding hit a wall

Man shocking a CRT monitor with defibrillator paddles in a dark room, sparks flying, illustrating stalled open-weight coding Models

SWE-bench Pro across open-weight models hasn't moved in 10 weeks

Mar 27th - Jun 1st. 5 major open-weight releases. Net progress on SWE-bench Pro: +0.3%. Scores swung -5% and back within that window

Looks like open-weight labs are optimizing hard for agent tasks and multimodality – but not for coding anymore

Table comparing five open-weight models on SWE-bench Pro from March to June 2026, scores clustered between 55.4 and 59

What SWE-bench Pro measures

SWE-bench Pro is Scale AI's coding benchmark for AI agents. Each task is a real issue from a professional code repository, and the model has to write a patch that passes the project's tests. The tasks are longer and harder than in the older SWE-bench Verified, so scores sit much lower.

Ten weeks without a new high

GLM 5.1 opened the window on March 27 with 58.4%. Three April releases followed. Kimi K2.6 scored 58.6%, shown as 59 in the table. MiMo V2.5 Pro scored 57.2%, and DeepSeek V4 Pro 55.4%. MiniMax M3 closed the window on June 1 with 59.0%.

The best open-weight score moved by less than one point in ten weeks. GPT-5.5 sat at the same level, 58.6%. Claude Opus 4.8 was far ahead at 69.2%.

The launch posts put the weight elsewhere. MiniMax led its M3 announcement with three things at once: coding, agent benchmarks such as Terminal Bench 2.1 and MCP Atlas, and a 1M-token context.

Update, October 19, 2026: the wall broke, then the benchmark changed

Two weeks after this post, Z.ai released GLM-5.2 with 62.1% on SWE-bench Pro, 3.1 points above MiniMax M3. It was the last major open-weight release to lead with that benchmark.

Kimi K3, DeepSeek V4 Pro 0813 and GLM-5.3 publish no SWE-bench Pro score in their model cards. They report DeepSWE, Terminal Bench and SWE-Marathon instead, which test longer, more agent-like coding work.

On DeepSWE, open-weight models now sit close to the closed frontier. The scores below come from the GLM-5.3 model card:

ModelWeightsDeepSWE v1.1
GPT-5.6 SolClosed72.7
Claude Fable 5Closed69.7
Kimi K3Open67.5
GLM-5.3Open66.9
DeepSeek V4 Pro 0813Open62.7
Claude Opus 4.8Closed58.0
GLM-5.2Open46.2

GLM-5.3 went from 46.2 to 66.9 in one release. Open-weight coding did not stop improving after June. The progress moved to benchmarks where it is still visible.

Sources

Portrait of Addy Crezee, author at thehype.news

Addy Crezee

Founder, CEO & Editor-in-Chief at thehype. Addy is a serial entrepreneur building products and communities since 2014. In 2024, he founded /function1, one of the largest AI conferences in the world, scaling from 0 to 10k attendees in its first year.

More articles by Addy Crezee →
On air · radio.thehype.news ↗ AI news radio — 24/7