A benchmark developed by Stanford University and the Laude Institute to evaluate AI agents in realistic terminal environments.
Browse the latest scores, model modes, release dates, and parameter sizes for TerminalBench 2.1.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| Rank | Model | License | |||
|---|---|---|---|---|---|
![]() GPT-5.6 Sol Thinking Level · Max | 88.80 | 2026-06-26 | Unknown | Closed | |
![]() Kimi K3 Thinking Level · MaxTools | 88.30 | 2026-07-16 | 2800B | Free Commercial | |
![]() Claude Fable 5 Thinking Level · HighTools | 88.00 | 2026-06-09 | Unknown | Closed | |
4 | ![]() Claude Fable 5 Deep Thinking ModeTools | 88.00 | 2026-06-09 | Unknown | Closed |
5 | ![]() GPT-5.6 Terra Thinking Level · Max | 87.40 | 2026-06-26 | Unknown | Closed |
6 | ![]() GPT-5.6 Luna Thinking Level · Max | 84.70 | 2026-06-26 | Unknown | Closed |
7 | ![]() GPT-5.5 Thinking Level · HighTools | 83.40 | 2026-04-23 | Unknown | Closed |
8 | Grok 4.5 Thinking Level · HighTools | 83.30 | 2026-07-08 | Unknown | Closed |
9 | ![]() GLM-5.2 Thinking Level · HighTools | 81.00 | 2026-06-13 | 753.3B | Free Commercial |
10 | ![]() Claude Sonnet 5 Thinking Level · Extra HighTools | 80.40 | 2026-06-30 | Unknown | Closed |
11 | ![]() Muse Spark 1.1 Thinking EnabledTools | 80.00 | 2026-07-09 | Unknown | Closed |
12 | ![]() Claude Opus 4.8 Thinking Level · HighTools | 78.90 | 2026-05-28 | Unknown | Closed |
13 | ![]() Gemini 3.5 Flash Thinking Level · HighTools | 76.20 | 2026-06-20 | Unknown | Closed |
14 | ![]() Gemini 3 Pro Thinking Level · HighTools | 74.40 | 2026-02-01 | Unknown | Closed |
15 | ![]() Hy3 Thinking Level · HighTools | 71.70 | 2026-07-06 | 295B | Free Commercial |
16 | ![]() Seed2.1 Pro Thinking EnabledTools | 71.00 | 2026-06-23 | Unknown | Closed |
17 | ![]() Gemini 3.1 Pro Preview Thinking Level · HighTools | 70.70 | 2026-02-20 | Unknown | Closed |
18 | ![]() Opus 4.7 Thinking Level · HighTools | 69.70 | 2026-04-16 | Unknown | Closed |
19 | ![]() Kimi K2.7 Code Thinking EnabledTools | 67.04 | 2026-06-12 | 1000B | Free Commercial |
20 | ![]() MiniMax M3 Thinking EnabledTools | 66.00 | 2026-06-01 | 428B | Non-Commercial |
21 | Inkling Thinking EnabledTools | 63.80 | 2026-07-15 | 975B | Free Commercial |
22 | ![]() Step 3.7 Flash Thinking EnabledTools | 59.50 | 2026-05-29 | 198B | Free Commercial |
23 | ![]() GLM 5.1 Thinking Level · HighTools | 58.70 | 2026-03-27 | 75.4B | Free Commercial |
24 | ![]() Gemini 3.0 Flash Thinking Level · HighTools | 58.00 | 2025-12-17 | Unknown | Closed |
25 | ![]() Kimi K2.6 Thinking Enabled | 53.56 | 2026-04-20 | 1000B | Free Commercial |