CC-Bench-V2 Backend

GLM-5 25.8%

Claude Opus 4.5 26.9% leads since February 2026

Fading

Labs’ own numbers All independent runs Include claimed scores

Agents change 85 real backend codebases in six languages. A task passes only when all of its unit tests pass.

In-house Z.ai evaluation. The tasks are not public.

Made by: Zhipu AI (Z.ai)
Released: February 2026
Kind: Fixing real repositories
Level: Expert
Scored: Checked automatically
Answers: Agent task
Tasks: Kept private

Strongest model tested: Claude Opus 4.5 #61 on the capability index
Last in a launch post: April 2026, dropped before it saturated
Last model added: April 2026
Scores refreshed: November 12th, 2026

Paper arxiv.org

Models scored in lab cards

Launch post lists it, from 1 lab

System card reports it, from 1 lab

GLM-5 leads with 25.8%

Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.

Claude Opus 4.5 leads with 26.9% across all independent runs

Best score per model across the official leaderboard, Epoch AI’s own runs and any board Epoch AI copied. Each bar and row names its source.

Claude Opus 4.5 leads with 26.9%, claims included

Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model.

Bars Table

1 GLM-5 25.8%
2 GLM-5V-Turbo 22.8%

Source: Labs’ model cards

1 Claude Opus 4.5 26.9%
2 GLM-5 25.8%
3 GLM-4.7 19.6%

Source: Official CC-Bench-V2 Backend leaderboard

1 Claude Opus 4.5 26.9%
2 GLM-5 25.8%
3 GLM-5V-Turbo 22.8%
4 GLM-4.7 19.6%

Sources: Official CC-Bench-V2 Backend leaderboard and labs’ model cards

#	Model	Score	Setting	Date	Source
1	GLM-5	25.8%		Feb 2026	Lab model card
2	GLM-5V-Turbo	22.8%		Apr 2026	Lab model card

#	Model	Score	Date	Source
1	Claude Opus 4.5	26.9%	Nov 2025	Official leaderboard
2	GLM-5	25.8%	Feb 2026	Official leaderboard
3	GLM-4.7	19.6%	Dec 2025	Official leaderboard

#	Model	Score	Date	Source
1	Claude Opus 4.5	26.9%	Nov 2025	Official leaderboard
2	GLM-5	25.8%	Feb 2026	Official leaderboard
3	GLM-5V-Turbo	22.8%	Apr 2026	Lab model card
4	GLM-4.7	19.6%	Dec 2025	Official leaderboard

The benchmark's own leaderboard has 3 models. Switch the scores above to rank them together.

Number one over time Number one over time Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

Anthropic

Own leaderboard Not tested since Feb 2026

Claude Opus 4.5 26.9%

Source: Official CC-Bench-V2 Backend leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Reported by the lab in its model card

Sources: Official CC-Bench-V2 Backend leaderboard and labs’ model cards

Labs headline it less often now, last in April 2026

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

Z.ai

Date	Launch post	Score	As the post writes it
Apr 1, 2026	GLM-5V-Turbo	22.8	CC-Backend 22.8

One system card reports it

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

Date	Document	Score	As the document writes it	Section
Feb 17, 2026	GLM-5 technical report	25.8	CC-Bench-V2 Backend Engineering, Pass@1 (Table 8)	Capabilities

One lab claim next to the leaderboard

Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. 1 of them match, which usually means one side copied the other. Every benchmark.

Model	Lab says	Board says	Gap
GLM-5	25.8% CC-Bench-V2 Backend Engineering, Pass@1 (Table 8)	25.8% Leaderboard	Same