ZeroBench-main w/ tools
ZeroBench main split evaluated with tool access. DeepSeek V4.1 Flash launch materials report Pass@5 with the Claude Code harness and a 512k-token context window.
Models ranked
2
tracked on this benchmark
Score band
63.0 – 49.0
best → lowest tracked
Snapshot trend
+14.00
Sep 10 → Oct 23 · 1 models
Leaderboard
Tracked models ranked by Pass@5 (higher is better).
Notes: Moonshot self-reported launch table, row 'ZeroBench_main w/ python (pass@5)', column 'Kimi K3.1 Pro (max)'. Settings: reasoning effort max, temperature 1.0, top-p 0.95 (blog footnote).
How to read this benchmark
This benchmark scores models where higher is better. Use scores for directional filtering and shortlisting, not universal quality ranking; then validate pricing, context window, provider availability, and fit for your workload.
Trust this score when
- There is a fresh timestamped snapshot (or multiple snapshots) for this benchmark.
- The model list covers the same version family you can actually deploy today.
- Top candidates overlap with your required routing and feature requirements.
Be cautious when
- There is only one benchmark snapshot or the dataset appears stale.
- The benchmark metric direction is opposite of your decision objective.
- The score difference between options is narrow and likely within implementation variance.
Related benchmarks
Last reviewed: Sep 10, 2026