| ★ | Codex / GPT-5.5 Rank 1 on terminal-bench@2.0. Agent: Codex. Model: GPT-5.5. Date: 2026-04-23. Official leaderboard reports 82.0% +/- 2.2. | 82 | terminal-bench-official |
| 2 | ForgeCode / GPT-5.4 Rank 2 on terminal-bench@2.0. Agent org: ForgeCode. Model org: OpenAI. Date: 2026-03-12. Official leaderboard reports 81.8% +/- 2.0. | 81.8 | terminal-bench-official |
| 3 | TongAgents / Gemini 3.1 Pro Rank 3 on terminal-bench@2.0. Agent org: BIGAI. Model org: Google. Date: 2026-03-13. Official leaderboard reports 80.2% +/- 2.6. | 80.2 | terminal-bench-official |
| 4 | ForgeCode / Claude Opus 4.6 Rank 4 on terminal-bench@2.0. Agent org: ForgeCode. Model org: Anthropic. Date: 2026-03-12. Official leaderboard reports 79.8% +/- 1.6. | 79.8 | terminal-bench-official |
| 5 | SageAgent / GPT-5.3-Codex Rank 5 on terminal-bench@2.0. Agent org: OpenSage. Model org: OpenAI. Date: 2026-03-13. Official leaderboard reports 78.4% +/- 2.2. | 78.4 | terminal-bench-official |
| 6 | ForgeCode / Gemini 3.1 Pro Rank 6 on terminal-bench@2.0. Agent org: ForgeCode. Model org: Google. Date: 2026-03-02. Official leaderboard reports 78.4% +/- 1.8. | 78.4 | terminal-bench-official |
| 7 | Droid / GPT-5.3-Codex Rank 7 on terminal-bench@2.0. Agent org: Factory. Model org: OpenAI. Date: 2026-02-24. Official leaderboard reports 77.3% +/- 2.2. | 77.3 | terminal-bench-official |
| 8 | Capy / Claude Opus 4.6 Rank 8 on terminal-bench@2.0. Agent org: Capy. Model org: Anthropic. Date: 2026-03-12. Official leaderboard reports 75.3% +/- 2.4. | 75.3 | terminal-bench-official |
| 9 | Simple Codex / GPT-5.3-Codex Rank 9 on terminal-bench@2.0. Agent org: OpenAI. Model org: OpenAI. Date: 2026-02-06. Official leaderboard reports 75.1% +/- 2.4. | 75.1 | terminal-bench-official |
| 10 | Terminus-KIRA / Gemini 3.1 Pro Rank 10 on terminal-bench@2.0. Agent org: KRAFTON AI. Model org: Google. Date: 2026-02-23. Official leaderboard reports 74.8% +/- 2.6. | 74.8 | terminal-bench-official |
| 11 | Terminus-KIRA / Claude Opus 4.6 Rank 11 on terminal-bench@2.0. Agent org: KRAFTON AI. Model org: Anthropic. Date: 2026-02-22. Official leaderboard reports 74.7% +/- 2.6. | 74.7 | terminal-bench-official |
| 12 | Mux / GPT-5.3-Codex Rank 12 on terminal-bench@2.0. Agent org: Coder. Model org: OpenAI. Date: 2026-03-06. Official leaderboard reports 74.6% +/- 2.5. | 74.6 | terminal-bench-official |
| 13 | MAYA-V2 / Claude 4.6 Opus Rank 13 on terminal-bench@2.0. Agent org: ADYA. Model org: Anthropic. Date: 2026-03-12. Official leaderboard reports 72.1% +/- 2.2. | 72.1 | terminal-bench-official |
| 14 | TongAgents / Claude Opus 4.6 Rank 14 on terminal-bench@2.0. Agent org: Bigai. Model org: Anthropic. Date: 2026-02-22. Official leaderboard reports 71.9% +/- 2.7. | 71.9 | terminal-bench-official |
| 15 | Junie CLI / Multiple Rank 15 on terminal-bench@2.0. Agent org: JetBrains. Model org: Multiple. Date: 2026-03-07. Official leaderboard reports 71.0% +/- 2.9. | 71 | terminal-bench-official |
| 16 | CodeBrain-1 / GPT-5.3-Codex Rank 16 on terminal-bench@2.0. Agent org: Feeling AI. Model org: OpenAI. Date: 2026-02-10. Official leaderboard reports 70.3% +/- 2.6. | 70.3 | terminal-bench-official |
| 17 | Droid / Claude Opus 4.6 Rank 17 on terminal-bench@2.0. Agent org: Factory. Model org: Anthropic. Date: 2026-02-05. Official leaderboard reports 69.9% +/- 2.5. | 69.9 | terminal-bench-official |
| 18 | Ante / Gemini 3 Pro Rank 18 on terminal-bench@2.0. Agent org: Antigma Labs. Model org: Google. Date: 2026-01-06. Official leaderboard reports 69.4% +/- 2.1. | 69.4 | terminal-bench-official |
| 19 | IndusAGI Coding Agent / GPT-5.3-Codex Rank 19 on terminal-bench@2.0. Agent org: Varun Israni (SoloVpx). Model org: OpenAI. Date: 2026-03-18. Official leaderboard reports 69.1% +/- 2.3. | 69.1 | terminal-bench-official |
| 20 | Crux / Claude Opus 4.6 Rank 20 on terminal-bench@2.0. Agent org: Roam. Model org: Anthropic. Date: 2026-02-23. Official leaderboard reports 66.9% +/- N/A. | 66.9 | terminal-bench-official |