BR-00141-006 |
GPT-4.1 |
Terminal-Bench Hard |
Overall |
13.6% |
Unknown |
Primary source ↗
|
OPNAI-41 |
BR-0015-007 |
GPT-5 |
Terminal-Bench Hard |
Overall |
32.6% |
Unknown |
Primary source ↗
|
OPNAI-5 |
BR-0015-021 |
GPT-5 |
Terminal-Bench Hard |
Overall |
37.9% |
Unknown |
Primary source ↗
|
OPNAI-5 |
BR-0015-033 |
GPT-5 |
Terminal-Bench Hard |
Overall |
26.5% |
Unknown |
Primary source ↗
|
OPNAI-5 |
BR-0015-045 |
GPT-5 |
Terminal-Bench Hard |
Overall |
18.2% |
Unknown |
Primary source ↗
|
OPNAI-5 |
BR-00151-007 |
GPT-5.1 |
Terminal-Bench Hard |
Overall |
45.5% |
Unknown |
Primary source ↗
|
OPNAI-51 |
BR-00151-021 |
GPT-5.1 |
Terminal-Bench Hard |
Overall |
22.7% |
Unknown |
Primary source ↗
|
OPNAI-51 |
BR-00152-006 |
GPT-5.2 |
Terminal-Bench Hard |
Overall |
47% |
Unknown |
Primary source ↗
|
OPNAI-52 |
BR-00152-018 |
GPT-5.2 |
Terminal-Bench Hard |
Overall |
31.8% |
Unknown |
Primary source ↗
|
OPNAI-52 |
BR-00152-030 |
GPT-5.2 |
Terminal-Bench Hard |
Overall |
43.2% |
Unknown |
Primary source ↗
|
OPNAI-52 |
BR-00154-007 |
GPT-5.4 |
Terminal-Bench Hard |
Overall |
37.9% |
Unknown |
Primary source ↗
|
OPNAI-54 |
BR-00154-019 |
GPT-5.4 |
Terminal-Bench Hard |
Overall |
43.2% |
Unknown |
Primary source ↗
|
OPNAI-54 |
BR-00154-032 |
GPT-5.4 |
Terminal-Bench Hard |
Overall |
57.6% |
Unknown |
Primary source ↗
|
OPNAI-54 |
BR-00155-019 |
GPT-5.5 |
Terminal-Bench Hard |
Overall |
60.6% |
Unknown |
Primary source ↗
|
OPNAI-55 |
BR-00155-034 |
GPT-5.5 |
Terminal-Bench Hard |
Overall |
57.6% |
Unknown |
Primary source ↗
|
OPNAI-55 |
BR-00155-047 |
GPT-5.5 |
Terminal-Bench Hard |
Overall |
49.2% |
Unknown |
Primary source ↗
|
OPNAI-55 |
BR-00155-060 |
GPT-5.5 |
Terminal-Bench Hard |
Overall |
59.8% |
Unknown |
Primary source ↗
|
OPNAI-55 |
BR-00155-073 |
GPT-5.5 |
Terminal-Bench Hard |
Overall |
52.3% |
Unknown |
Primary source ↗
|
OPNAI-55 |
BR-00156SL-008 |
GPT-5.6 Sol |
Terminal-Bench Hard |
Overall |
60.6% |
Unknown |
Primary source ↗
|
OPNAI-56SL |
BR-00156SL-022 |
GPT-5.6 Sol |
Terminal-Bench Hard |
Overall |
62.9% |
Unknown |
Primary source ↗
|
OPNAI-56SL |
BR-00156SL-047 |
GPT-5.6 Sol |
Terminal-Bench Hard |
Overall |
62.1% |
Unknown |
Primary source ↗
|
OPNAI-56SL |
BR-00156SL-061 |
GPT-5.6 Sol |
Terminal-Bench Hard |
Overall |
65.9% |
Unknown |
Primary source ↗
|
OPNAI-56SL |
BR-00156SL-076 |
GPT-5.6 Sol |
Terminal-Bench Hard |
Overall |
61.4% |
Unknown |
Primary source ↗
|
OPNAI-56SL |
BR-00156TR-021 |
GPT-5.6 Terra |
Terminal-Bench Hard |
Overall |
57.6% |
Unknown |
Primary source ↗
|
OPNAI-56TR |
BR-00156TR-046 |
GPT-5.6 Terra |
Terminal-Bench Hard |
Overall |
62.9% |
Unknown |
Primary source ↗
|
OPNAI-56TR |
BR-00156TR-060 |
GPT-5.6 Terra |
Terminal-Bench Hard |
Overall |
57.6% |
Unknown |
Primary source ↗
|
OPNAI-56TR |
BR-00156TR-075 |
GPT-5.6 Terra |
Terminal-Bench Hard |
Overall |
43.9% |
Unknown |
Primary source ↗
|
OPNAI-56TR |
BR-002FB5-008 |
Claude Fable 5 |
Terminal-Bench Hard |
Overall |
62.9% |
Unknown |
Primary source ↗
|
ANTHR-FB5 |
BR-002H3-006 |
Claude 3 Haiku |
Terminal-Bench Hard |
Overall |
0.8% |
Unknown |
Primary source ↗
|
ANTHR-H3 |
BR-002H35-007 |
Claude 3.5 Haiku |
Terminal-Bench Hard |
Overall |
2.3% |
Unknown |
Primary source ↗
|
ANTHR-H35 |
BR-002H45-007 |
Claude 4.5 Haiku |
Terminal-Bench Hard |
Overall |
27.3% |
Unknown |
Primary source ↗
|
ANTHR-H45 |
BR-002H45-022 |
Claude 4.5 Haiku |
Terminal-Bench Hard |
Overall |
27.3% |
Unknown |
Primary source ↗
|
ANTHR-H45 |
BR-002O4-012 |
Claude 4 Opus |
Terminal-Bench Hard |
Overall |
31.1% |
Unknown |
Primary source ↗
|
ANTHR-O4 |
BR-002O41-006 |
Claude 4.1 Opus |
Terminal-Bench Hard |
Overall |
34.3% |
Unknown |
Primary source ↗
|
ANTHR-O41 |
BR-002O45-006 |
Claude Opus 4.5 |
Terminal-Bench Hard |
Overall |
47% |
Unknown |
Primary source ↗
|
ANTHR-O45 |
BR-002O45-018 |
Claude Opus 4.5 |
Terminal-Bench Hard |
Overall |
40.9% |
Unknown |
Primary source ↗
|
ANTHR-O45 |
BR-002O46-006 |
Claude Opus 4.6 |
Terminal-Bench Hard |
Overall |
48.5% |
Unknown |
Primary source ↗
|
ANTHR-O46 |
BR-002O46-018 |
Claude Opus 4.6 |
Terminal-Bench Hard |
Overall |
46.2% |
Unknown |
Primary source ↗
|
ANTHR-O46 |
BR-002O47-014 |
Claude Opus 4.7 |
Terminal-Bench Hard |
Overall |
54.5% |
Unknown |
Primary source ↗
|
ANTHR-O47 |
BR-002O47-025 |
Claude Opus 4.7 |
Terminal-Bench Hard |
Overall |
51.5% |
Unknown |
Primary source ↗
|
ANTHR-O47 |
BR-002O48-027 |
Claude Opus 4.8 |
Terminal-Bench Hard |
Overall |
58.3% |
Unknown |
Primary source ↗
|
ANTHR-O48 |
BR-002S37-006 |
Claude 3.7 Sonnet |
Terminal-Bench Hard |
Overall |
21.2% |
Unknown |
Primary source ↗
|
ANTHR-S37 |
BR-002S37-017 |
Claude 3.7 Sonnet |
Terminal-Bench Hard |
Overall |
21.2% |
Unknown |
Primary source ↗
|
ANTHR-S37 |
BR-002S4-007 |
Claude 4 Sonnet |
Terminal-Bench Hard |
Overall |
31.1% |
Unknown |
Primary source ↗
|
ANTHR-S4 |
BR-002S4-021 |
Claude 4 Sonnet |
Terminal-Bench Hard |
Overall |
27.3% |
Unknown |
Primary source ↗
|
ANTHR-S4 |
BR-002S45-007 |
Claude 4.5 Sonnet |
Terminal-Bench Hard |
Overall |
35.6% |
Unknown |
Primary source ↗
|
ANTHR-S45 |
BR-002S45-021 |
Claude 4.5 Sonnet |
Terminal-Bench Hard |
Overall |
28.8% |
Unknown |
Primary source ↗
|
ANTHR-S45 |
BR-002S46-007 |
Claude Sonnet 4.6 |
Terminal-Bench Hard |
Overall |
46.2% |
Unknown |
Primary source ↗
|
ANTHR-S46 |
BR-002S46-020 |
Claude Sonnet 4.6 |
Terminal-Bench Hard |
Overall |
53% |
Unknown |
Primary source ↗
|
ANTHR-S46 |
BR-002S46-036 |
Claude Sonnet 4.6 |
Terminal-Bench Hard |
Overall |
42.4% |
Unknown |
Primary source ↗
|
ANTHR-S46 |
BR-00325F-006 |
Gemini 2.5 Flash |
Terminal-Bench Hard |
Overall |
13.6% |
Unknown |
Primary source ↗
|
GOOGL-G25F |
BR-00325F-018 |
Gemini 2.5 Flash |
Terminal-Bench Hard |
Overall |
12.1% |
Unknown |
Primary source ↗
|
GOOGL-G25F |
BR-00325P-007 |
Gemini 2.5 Pro |
Terminal-Bench Hard |
Overall |
26.5% |
Unknown |
Primary source ↗
|
GOOGL-G25P |
BR-00335F-009 |
Gemini 3.5 Flash |
Terminal-Bench Hard |
Overall |
40.9% |
Unknown |
Primary source ↗
|
GOOGL-G35F |
BR-00335F-023 |
Gemini 3.5 Flash |
Terminal-Bench Hard |
Overall |
46.2% |
Unknown |
Primary source ↗
|
GOOGL-G35F |
BR-00335F-033 |
Gemini 3.5 Flash |
Terminal-Bench Hard |
Overall |
39.4% |
Unknown |
Primary source ↗
|
GOOGL-G35F |
BR-0043-006 |
Grok 3 |
Terminal-Bench Hard |
Overall |
11.4% |
Unknown |
Primary source ↗
|
XAI-G3 |
BR-0044-006 |
Grok 4 |
Terminal-Bench Hard |
Overall |
37.9% |
Unknown |
Primary source ↗
|
XAI-G4 |
BR-00443-006 |
Grok 4.3 |
Terminal-Bench Hard |
Overall |
30.3% |
Unknown |
Primary source ↗
|
XAI-G43 |
BR-00443-019 |
Grok 4.3 |
Terminal-Bench Hard |
Overall |
18.9% |
Unknown |
Primary source ↗
|
XAI-G43 |
BR-00443-034 |
Grok 4.3 |
Terminal-Bench Hard |
Overall |
37.9% |
Unknown |
Primary source ↗
|
XAI-G43 |
BR-00443-050 |
Grok 4.3 |
Terminal-Bench Hard |
Overall |
26.5% |
Unknown |
Primary source ↗
|
XAI-G43 |
BR-007QWEN25INSTRUCT72B-006 |
Qwen2.5 Instruct 72B |
Terminal-Bench Hard |
Overall |
4.5% |
Unknown |
Primary source ↗
|
QWEN-QWEN25INSTRUCT72B |
BR-007QWEN306B-006 |
Qwen3 0.6B |
Terminal-Bench Hard |
Overall |
0% |
Unknown |
Primary source ↗
|
QWEN-QWEN306B |
BR-007QWEN306B-017 |
Qwen3 0.6B |
Terminal-Bench Hard |
Overall |
0% |
Unknown |
Primary source ↗
|
QWEN-QWEN306B |
BR-007QWEN314B-007 |
Qwen3 14B |
Terminal-Bench Hard |
Overall |
3.8% |
Unknown |
Primary source ↗
|
QWEN-QWEN314B |
BR-007QWEN314B-020 |
Qwen3 14B |
Terminal-Bench Hard |
Overall |
5.3% |
Unknown |
Primary source ↗
|
QWEN-QWEN314B |
BR-007QWEN317B-006 |
Qwen3 1.7B |
Terminal-Bench Hard |
Overall |
0% |
Unknown |
Primary source ↗
|
QWEN-QWEN317B |
BR-007QWEN317B-017 |
Qwen3 1.7B |
Terminal-Bench Hard |
Overall |
0% |
Unknown |
Primary source ↗
|
QWEN-QWEN317B |
BR-007QWEN3235BA22B-006 |
Qwen3 235B A22B |
Terminal-Bench Hard |
Overall |
6.1% |
Unknown |
Primary source ↗
|
QWEN-QWEN3235BA22B |
BR-007QWEN3235BA22B-017 |
Qwen3 235B A22B |
Terminal-Bench Hard |
Overall |
6.1% |
Unknown |
Primary source ↗
|
QWEN-QWEN3235BA22B |
BR-007QWEN3235BA22B2507-007 |
Qwen3 235B A22B 2507 |
Terminal-Bench Hard |
Overall |
13.6% |
Unknown |
Primary source ↗
|
QWEN-QWEN3235BA22B2507 |
BR-007QWEN3235BA22B2507INSTRUCT-006 |
Qwen3 235B A22B 2507 Instruct |
Terminal-Bench Hard |
Overall |
15.2% |
Unknown |
Primary source ↗
|
QWEN-QWEN3235BA22B2507INSTRUCT |
BR-007QWEN330BA3B-006 |
Qwen3 30B A3B |
Terminal-Bench Hard |
Overall |
2.3% |
Unknown |
Primary source ↗
|
QWEN-QWEN330BA3B |
BR-007QWEN330BA3B-017 |
Qwen3 30B A3B |
Terminal-Bench Hard |
Overall |
6.8% |
Unknown |
Primary source ↗
|
QWEN-QWEN330BA3B |
BR-007QWEN330BA3B2507-007 |
Qwen3 30B A3B 2507 |
Terminal-Bench Hard |
Overall |
5.3% |
Unknown |
Primary source ↗
|
QWEN-QWEN330BA3B2507 |
BR-007QWEN330BA3B2507INSTRUCT-006 |
Qwen3 30B A3B 2507 Instruct |
Terminal-Bench Hard |
Overall |
6.1% |
Unknown |
Primary source ↗
|
QWEN-QWEN330BA3B2507INSTRUCT |
BR-007QWEN332B-007 |
Qwen3 32B |
Terminal-Bench Hard |
Overall |
3% |
Unknown |
Primary source ↗
|
QWEN-QWEN332B |
BR-007QWEN34B2507-006 |
Qwen3 4B 2507 |
Terminal-Bench Hard |
Overall |
1.5% |
Unknown |
Primary source ↗
|
QWEN-QWEN34B2507 |
BR-007QWEN34B2507INSTRUCT-006 |
Qwen3 4B 2507 Instruct |
Terminal-Bench Hard |
Overall |
4.5% |
Unknown |
Primary source ↗
|
QWEN-QWEN34B2507INSTRUCT |
BR-007QWEN3508B-006 |
Qwen3.5 0.8B |
Terminal-Bench Hard |
Overall |
0% |
Unknown |
Primary source ↗
|
QWEN-QWEN3508B |
BR-007QWEN3508B-021 |
Qwen3.5 0.8B |
Terminal-Bench Hard |
Overall |
0% |
Unknown |
Primary source ↗
|
QWEN-QWEN3508B |
BR-007QWEN35122BA10B-007 |
Qwen3.5 122B A10B |
Terminal-Bench Hard |
Overall |
29.5% |
Unknown |
Primary source ↗
|
QWEN-QWEN35122BA10B |
BR-007QWEN35122BA10B-022 |
Qwen3.5 122B A10B |
Terminal-Bench Hard |
Overall |
31.1% |
Unknown |
Primary source ↗
|
QWEN-QWEN35122BA10B |
BR-007QWEN3527B-006 |
Qwen3.5 27B |
Terminal-Bench Hard |
Overall |
32.6% |
Unknown |
Primary source ↗
|
QWEN-QWEN3527B |
BR-007QWEN3527B-019 |
Qwen3.5 27B |
Terminal-Bench Hard |
Overall |
31.8% |
Unknown |
Primary source ↗
|
QWEN-QWEN3527B |
BR-007QWEN352B-007 |
Qwen3.5 2B |
Terminal-Bench Hard |
Overall |
3.8% |
Unknown |
Primary source ↗
|
QWEN-QWEN352B |
BR-007QWEN352B-022 |
Qwen3.5 2B |
Terminal-Bench Hard |
Overall |
3.8% |
Unknown |
Primary source ↗
|
QWEN-QWEN352B |
BR-007QWEN3535BA3B-006 |
Qwen3.5 35B A3B |
Terminal-Bench Hard |
Overall |
26.5% |
Unknown |
Primary source ↗
|
QWEN-QWEN3535BA3B |
BR-007QWEN3535BA3B-019 |
Qwen3.5 35B A3B |
Terminal-Bench Hard |
Overall |
10.6% |
Unknown |
Primary source ↗
|
QWEN-QWEN3535BA3B |
BR-007QWEN35397BA17B-007 |
Qwen3.5 397B A17B |
Terminal-Bench Hard |
Overall |
40.9% |
Unknown |
Primary source ↗
|
QWEN-QWEN35397BA17B |
BR-007QWEN35397BA17B-023 |
Qwen3.5 397B A17B |
Terminal-Bench Hard |
Overall |
35.6% |
Unknown |
Primary source ↗
|
QWEN-QWEN35397BA17B |
BR-007QWEN354B-007 |
Qwen3.5 4B |
Terminal-Bench Hard |
Overall |
11.4% |
Unknown |
Primary source ↗
|
QWEN-QWEN354B |
BR-007QWEN354B-021 |
Qwen3.5 4B |
Terminal-Bench Hard |
Overall |
18.2% |
Unknown |
Primary source ↗
|
QWEN-QWEN354B |
BR-007QWEN359B-007 |
Qwen3.5 9B |
Terminal-Bench Hard |
Overall |
18.2% |
Unknown |
Primary source ↗
|
QWEN-QWEN359B |
BR-007QWEN359B-021 |
Qwen3.5 9B |
Terminal-Bench Hard |
Overall |
24.2% |
Unknown |
Primary source ↗
|
QWEN-QWEN359B |
BR-007QWEN35OMNIFLASH-006 |
Qwen3.5 Omni Flash |
Terminal-Bench Hard |
Overall |
8.3% |
Unknown |
Primary source ↗
|
QWEN-QWEN35OMNIFLASH |
BR-007QWEN35OMNIPLUS-006 |
Qwen3.5 Omni Plus |
Terminal-Bench Hard |
Overall |
21.2% |
Unknown |
Primary source ↗
|
QWEN-QWEN35OMNIPLUS |
BR-007QWEN3627B-007 |
Qwen3.6 27B |
Terminal-Bench Hard |
Overall |
21.2% |
Unknown |
Primary source ↗
|
QWEN-QWEN3627B |
BR-007QWEN3627B-022 |
Qwen3.6 27B |
Terminal-Bench Hard |
Overall |
34.8% |
Unknown |
Primary source ↗
|
QWEN-QWEN3627B |