GPT-5.5
OpenAI
Parameters
—
Architecture
—
Released
—
License
—
About
No detailed description available for this model.
Benchmark Scores
| Benchmark | Score | Date | Standing |
|---|---|---|---|
|
Humanity's Last Exam
stem_reasoning
|
74.43%
|
17.06.2026 |
#16/71
better than 77%
|
|
CritPt (no tools)
stem_reasoning
|
83.60%
|
17.06.2026 |
#3/21
better than 90%
|
|
AIME 26
stem_reasoning
|
98.85%
|
17.06.2026 |
#4/45
better than 91%
|
|
HMMT Feb 26
stem_reasoning
|
98.70%
|
17.06.2026 |
#3/44
better than 93%
|
|
GPQA Diamond
stem_reasoning
|
98.68%
|
17.06.2026 |
#5/80
better than 95%
|
|
SWE-bench Pro
coding_agent
|
65.33%
|
17.06.2026 |
#20/77
better than 72%
|
|
NL2Repo
coding_agent
|
62.15%
|
17.06.2026 |
#14/41
better than 68%
|
|
DeepSWE 1.1
coding_agent
|
90.89%
|
17.06.2026 |
#7/34
better than 79%
|
|
ProgramBench
coding_agent
|
98.40%
|
17.06.2026 |
#2/18
better than 94%
|
|
Terminal-Bench 2.1 (Terminus-2)
coding_agent
|
92.92%
|
17.06.2026 |
#9/44
better than 81%
|
|
Terminal-Bench 2.1 (Best Reported Harness)
coding_agent
|
100.00%
|
17.06.2026 |
#1/5
better than 100%
|
|
PostTrainBench
coding_agent
|
52.22%
|
17.06.2026 |
#17/22
better than 24%
|
|
MCP-Atlas
general_agent
|
81.85%
|
17.06.2026 |
#16/54
better than 70%
|
|
Tool Decathlon
general_agent
|
91.02%
|
17.06.2026 |
#2/11
better than 90%
|
|
HLE (with tools)
stem_reasoning
|
68.27%
|
17.06.2026 |
#23/49
better than 54%
|
|
Program Bench
coding_agent
|
100.00%
|
23.08.2026 |
#1/7
better than 100%
|
|
MLS-Bench-Lite
coding_agent
|
37.93%
|
23.08.2026 |
#6/9
better than 38%
|
|
Kimi Claw 24/7 Bench
agentic
|
100.00%
|
23.08.2026 |
#1/4
better than 100%
|
|
MCPMark-Verified
agentic
|
100.00%
|
23.08.2026 |
#1/4
better than 100%
|
|
SWE-Marathon
coding_agent
|
21.70%
|
17.06.2026 |
#14/17
better than 19%
|
|
Kimi Code Bench V2
coding_agent
|
69.08%
|
23.08.2026 |
#3/7
better than 67%
|
|
FrontierSWE
coding_agent
|
73.65%
|
17.06.2026 |
#6/12
better than 55%
|
|
HMMT Nov 25
stem_reasoning
|
100.00%
|
17.06.2026 |
#1/20
better than 95%
|
What is a good Humanity's Last Exam score? What is a good CritPt (no tools) score? What is a good AIME 26 score?
No comments yet
Be the first to share your thoughts!