Skip to content
Hbench
hbench

Results

Results

Every published run, newest first, each with its own pass rate. Filter it, or download what you see as CSV.

56 runs

Download CSV

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

Results, one row per published run
HarnessBoardPass rateHigher is better, 95% intervalRunCost per taskhbenchFinished
little-coder
Terminal-Bench 2.0 on qwen3.6-35b-a3b (5 attempts, open network)23.8%17.1–31.2#103—converted26 Apr 2026
simplai-agent0.3.0
Terminal-Bench 2.0 on claude-sonnet-4-6 (5 attempts, open network)52.1%43.6–60.7#81—converted17 Apr 2026
just-another-coding-agent
Terminal-Bench 2.0 on glm-5 (5 attempts, open network)47.4%39.1–55.5#99—converted5 Apr 2026
Copilot CLI
Terminal-Bench 2.0 on Claude Opus 4.6 (5 attempts, open network)60.4%51.5–68.8#91—converted3 Apr 2026
wozcode2.1.86
Terminal-Bench 2.0 on Claude Opus 4.6 (5 attempts, open network)68.1%60.0–76.4#123$0.75converted29 Mar 2026
pilot
Terminal-Bench 2.0 on Claude Opus 4.6 (5 attempts, open network)82.0%74.2–88.5#105—converted28 Mar 2026
meta-harness1.1.0
Terminal-Bench 2.0 on Claude Opus 4.6 (5 attempts, open network)76.4%69.2–83.4#117$2.06converted26 Mar 2026
Gemini CLI
Terminal-Bench 2.0 on Gemini 3.1 Pro Preview (5 attempts, open network)59.8%51.5–68.1#115—converted25 Mar 2026
spoox-o-m
Terminal-Bench 2.0 on gpt-5-nano (5 attempts, open network)21.8%15.5–28.1#107—converted24 Mar 2026
Indusagi Coding Agent
Terminal-Bench 2.0 on MiniMax-M2.7 (5 attempts, open network)34.4%27.4–40.9#53—converted22 Mar 2026
Indusagi Coding Agent
Terminal-Bench 2.0 on GPT-5.3-Codex (5 attempts, open network)58.7%50.6–65.8#55—converted17 Mar 2026
spoox-o-m
Terminal-Bench 2.0 on GPT-5.3-Codex (5 attempts, open network)71.5%63.1–79.1#109$2.44converted17 Mar 2026
maya-v21.5-official
Terminal-Bench 2.0 on Claude Opus 4.6 (5 attempts, open network)71.9%63.4–79.6#67—converted9 Mar 2026
tongagents0.8.0
Terminal-Bench 2.0 on Gemini 3.1 Pro Preview (5 attempts, open network)80.2%73.5–85.8#133—converted9 Mar 2026
Gemini CLI
Terminal-Bench 2.0 on Gemini 3 Flash Preview (5 attempts, open network)47.4%38.7–55.7#113—converted5 Mar 2026
droid
Terminal-Bench 2.0 on GPT-5.3-Codex (5 attempts, open network)77.3%69.4–84.5#63—converted22 Feb 2026
Ante
Terminal-Bench 2.0 on Gemini 3.1 Pro Preview (5 attempts, open network)73.7%66.3–80.2#45—converted21 Feb 2026
sageagent
Terminal-Bench 2.0 on Gemini 3 Pro Preview (5 attempts, open network)65.2%56.0–73.5#79—converted13 Feb 2026
Judy0.7.0
Terminal-Bench 2.0 on Claude Opus 4.6 (5 attempts, open network)71.9%63.8–79.3#131—converted13 Feb 2026
mux
Terminal-Bench 2.0 on GPT-5.3-Codex (5 attempts, open network)74.6%67.0–81.6#75—converted12 Feb 2026
Terminus 22.0.0
Terminal-Bench 2.0 on deepseek-v3.2 (5 attempts, open network)39.6%31.5–48.1#121$0.03converted8 Feb 2026
Claude Code2.1.34
Terminal-Bench 2.0 on GLM-4.7 (5 attempts, open network)33.3%25.2–41.6#129—converted7 Feb 2026
hookele0.0.1
Terminal-Bench 2.0 on gpt-5.1-codex-mini (5 attempts, open network)61.1%51.2–70.1#125—converted6 Feb 2026
Terminus 22.0.0
Terminal-Bench 2.0 on Claude Opus 4.6 (5 attempts, open network)62.9%54.4–70.8#119$0.66converted6 Feb 2026
droid
Terminal-Bench 2.0 on Claude Opus 4.6 (5 attempts, open network)69.9%61.8–77.3#61—converted30 Jan 2026