Results

11 results

Terminal-Bench 4.0 — Codex results
ProviderModelScoreSourceRegistry No.
OpenAIGPT-6.1 Sol (max)58.2%tbench.ai for GPT-6.1 Sol (max) on Terminal-Bench 4.0 — Codex (opens in a new tab)Archived copy (opens in a new tab)Terminal-Bench AccuracyReported Benchmark leaderboardTerminal-BenchIndependentTerminal-Bench TeamRecord for GPT-6.1 Sol on Terminal-Bench 4.0 — Codex10015
OpenAIGPT-6 Luna (max)16.4%tbench.ai for GPT-6 Luna (max) on Terminal-Bench 4.0 — Codex (opens in a new tab)Archived copy (opens in a new tab)Terminal-Bench AccuracyReported Benchmark leaderboardTerminal-BenchIndependentTerminal-Bench TeamRecord for GPT-6 Luna on Terminal-Bench 4.0 — Codex10013
OpenAIGPT-6 Sol (max)49.4%tbench.ai for GPT-6 Sol (max) on Terminal-Bench 4.0 — Codex (opens in a new tab)Archived copy (opens in a new tab)Terminal-Bench AccuracyReported Benchmark leaderboardTerminal-BenchIndependentTerminal-Bench TeamRecord for GPT-6 Sol on Terminal-Bench 4.0 — Codex10014
OpenAIGPT-6 Astra (max)58.2%tbench.ai for GPT-6 Astra (max) on Terminal-Bench 4.0 — Codex (opens in a new tab)Archived copy (opens in a new tab)Terminal-Bench AccuracyReported Benchmark leaderboardTerminal-BenchIndependentTerminal-Bench TeamRecord for GPT-6 Astra on Terminal-Bench 4.0 — Codex10005
OpenAIGPT-6 Astra (xhigh)57.9%tbench.ai for GPT-6 Astra (xhigh) on Terminal-Bench 4.0 — Codex (opens in a new tab)Archived copy (opens in a new tab)Terminal-Bench AccuracyReported Benchmark leaderboardTerminal-BenchIndependentTerminal-Bench TeamRecord for GPT-6 Astra on Terminal-Bench 4.0 — Codex10005
OpenAIGPT-6 Astra (medium)54.2%tbench.ai for GPT-6 Astra (medium) on Terminal-Bench 4.0 — Codex (opens in a new tab)Archived copy (opens in a new tab)Terminal-Bench AccuracyReported Benchmark leaderboardTerminal-BenchIndependentTerminal-Bench TeamRecord for GPT-6 Astra on Terminal-Bench 4.0 — Codex10005
OpenAIGPT-6 Astra (high)57.9%tbench.ai for GPT-6 Astra (high) on Terminal-Bench 4.0 — Codex (opens in a new tab)Archived copy (opens in a new tab)Terminal-Bench AccuracyReported Benchmark leaderboardTerminal-BenchIndependentTerminal-Bench TeamRecord for GPT-6 Astra on Terminal-Bench 4.0 — Codex10005
OpenAIGPT-6 Astra (low)50.6%tbench.ai for GPT-6 Astra (low) on Terminal-Bench 4.0 — Codex (opens in a new tab)Archived copy (opens in a new tab)Terminal-Bench AccuracyReported Benchmark leaderboardTerminal-BenchIndependentTerminal-Bench TeamRecord for GPT-6 Astra on Terminal-Bench 4.0 — Codex10005
OpenAIGPT-5.6 Luna (max)17.3%tbench.ai for GPT-5.6 Luna (max) on Terminal-Bench 4.0 — Codex (opens in a new tab)Archived copy (opens in a new tab)Terminal-Bench AccuracyReported Benchmark leaderboardTerminal-BenchIndependentTerminal-Bench TeamRecord for GPT-5.6 Luna on Terminal-Bench 4.0 — Codex10009
OpenAIGPT-5.6 Sol (max)37.3%tbench.ai for GPT-5.6 Sol (max) on Terminal-Bench 4.0 — Codex (opens in a new tab)Archived copy (opens in a new tab)Terminal-Bench AccuracyReported Benchmark leaderboardTerminal-BenchIndependentTerminal-Bench TeamRecord for GPT-5.6 Sol on Terminal-Bench 4.0 — Codex10010
OpenAIGPT-5.6 Terra (max)21.5%tbench.ai for GPT-5.6 Terra (max) on Terminal-Bench 4.0 — Codex (opens in a new tab)Archived copy (opens in a new tab)Terminal-Bench AccuracyReported Benchmark leaderboardTerminal-BenchIndependentTerminal-Bench TeamRecord for GPT-5.6 Terra on Terminal-Bench 4.0 — Codex10011