INTELLECT-3 (based on GLM-4.5-Air)
Prime Intellect
Release Date
2025-11-27
Parameters
—
Context Length
—
Modalities
—
Capability Radar
32
general
78
coding
86
reasoning
57
science
84
agents
0
multimodal
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 314 | 48.0 | AA |
| General Ranking | 383 | 35.0 | AA |
| Science | 280 | 49.0 | AA |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))No benchmark data available
AA Evaluation Indices
(Artificial Analysis)Math Index(Artificial Analysis)88.0
Aime 25(MAA (Mathematical Association of America))88.0
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))82.2
Livecodebench(UC Berkeley + MIT + Cornell (2024))77.7
Gpqa(NYU + Cohere + Anthropic (2023))76.1
Lcr(Artificial Analysis)39.7
Ifbench(Google Research (2023))34.0
Tau2(Sierra + U Toronto + Vector Institute (2025))26.6
Hle(Center for AI Safety + Scale AI (2025))13.1
Intelligence Index(Artificial Analysis)10.6
Terminalbench Hard(Stanford × Laude Institute (2026))9.1
LLM Stats Category Scores
(LLM Stats (zeroeval))No category score data available
Pricing
Input PriceFree
Output PriceFree
Blended Price (3:1)Free
Speed
Tokens/sec0.0
Time to First Token0.00s
Time to Answer0.00s
Provider Price Ranking
No provider data available