Skip to content
Hbench
hbench

Results

Results

Every published result, one row per harness version on each board. Filter it, or download what you see as CSV.

56 results

Download CSV

Select two rows of one board to compare them task by task.

Results, one row per configuration on each board
HarnessBoardPass rateHigher is better, 95% intervalRunsCost per taskhbenchLast finished
Terminus 2
HumanEvalFix on Qwen2.5-Coder 7Bsample-40 task set, 1 attempt7.5%0.0–17.51—0.2.418 Oct 2026
DeepSeek Harness0.2.0-rc.2
SWE-bench Verified on Claude Opus 5.593.4%91.2–95.41—0.2.319 Oct 2026
Claude Code2.1.302
SWE-bench Verified on Claude Opus 5.590.8%88.2–93.21$0.160.2.319 Oct 2026
Codex0.163.0
Terminal-Bench 2.0 on GPT-5.6 Sol62.9%52.8–73.01—0.3.523 Oct 2026
Claude Code2.1.309
humaneval-plus@1.0 (unreviewed) on GPT-6 Sol95.1%91.5–98.21$0.070.3.624 Oct 2026
Codex0.164.0
humaneval-plus@1.0 (unreviewed) on GPT-6 Sol95.1%91.5–98.21$0.030.3.624 Oct 2026
Codex0.164.0
humaneval-plus@1.0 (unreviewed) on codex-auto-review94.5%90.9–97.61—0.3.624 Oct 2026
Claude Code2.1.309
humaneval-plus@1.0 (unreviewed) on codex-auto-review93.3%89.0–97.01$0.100.3.624 Oct 2026
Codex0.164.0
humaneval-plus@1.0 (unreviewed) on GPT-5.6 Luna95.7%92.7–98.81$0.0030.3.624 Oct 2026
Claude Code2.1.309
humaneval-plus@1.0 (unreviewed) on GPT-5.6 Luna93.9%90.2–97.61$0.100.3.624 Oct 2026
Claude Code2.1.309
humaneval-plus@1.0 (unreviewed) on GPT-5.6 Sol95.7%92.7–98.21$0.070.3.624 Oct 2026
Codex0.164.0
humaneval-plus@1.0 (unreviewed) on GPT-5.6 Terra95.7%92.7–98.21$0.030.3.624 Oct 2026
Claude Code2.1.309
humaneval-plus@1.0 (unreviewed) on GPT-5.6 Terra93.9%90.2–97.01$0.070.3.624 Oct 2026
DeepSeek Harness0.2.1-rc.2
humaneval-plus@1.0 (unreviewed) on GPT-6.1 Sol96.3%93.3–98.81—0.3.624 Oct 2026
Claude Code2.1.309
humaneval-plus@1.0 (unreviewed) on GPT-6.1 Sol95.7%92.7–98.21$0.070.3.624 Oct 2026
Codex0.164.0
humaneval-plus@1.0 (unreviewed) on GPT-6.1 Sol95.7%92.7–98.21$0.020.3.624 Oct 2026
Claude Code2.1.309
humaneval-plus@1.0 (unreviewed) on GPT-6 Astra96.3%93.3–98.81$0.060.3.624 Oct 2026
Codex0.164.0
humaneval-plus@1.0 (unreviewed) on GPT-6 Astra95.7%92.7–98.21$0.110.3.624 Oct 2026
Claude Code2.1.309
humaneval-plus@1.0 (unreviewed) on GPT-6 Luna92.7%88.4–96.31$0.060.3.624 Oct 2026
Codex0.164.0
humaneval-plus@1.0 (unreviewed) on GPT-6 Luna88.4%83.5–93.31$0.0010.3.624 Oct 2026
sageagent
Terminal-Bench 2.0 on Gemini 3 Pro Preview (5 attempts, open network)65.2%56.0–73.51—converted13 Feb 2026
Ante
Terminal-Bench 2.0 on Gemini 3 Pro Preview (5 attempts, open network)64.7%56.2–72.11—converted1 Jan 2026
tongagents0.8.0
Terminal-Bench 2.0 on Gemini 3.1 Pro Preview (5 attempts, open network)80.2%73.5–85.81—converted9 Mar 2026
Ante
Terminal-Bench 2.0 on Gemini 3.1 Pro Preview (5 attempts, open network)73.7%66.3–80.21—converted21 Feb 2026
Gemini CLI
Terminal-Bench 2.0 on Gemini 3.1 Pro Preview (5 attempts, open network)59.8%51.5–68.11—converted25 Mar 2026