INTELLECT-3
INTELLECT-3 is behind the leaders in agentic tasks and reasoning. Too few results yet to rate coding, safety, long context, math, multimodal tasks, multilingual tasks, instruction following, or factuality.
Capability profile
Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.
Too few results yet to rate Coding, Safety, Long Context, Math, Multimodal, Multilingual, Instruction Following or Factuality.
Price
$0.20input$1.10outputper million tokens
From prime-intellect · All prices
Evidence
15results on15benchmarks
- 15 aggregator
From 1 source · latest Oct 8, 2026 · How verification works
API features
Tool callingStructured outputsReasoning
As listed by OpenRouter
INTELLECT-3 benchmark results
15 results on 15 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
41.3% behind the leader1 of 7 ranked benchmarks measured
- 12.42Jun 15, 2026
41.7% behind the leader3 of 6 ranked benchmarks measured
- GPQA Diamond76.06Oct 8, 2026gpqa
- Humanity's Last Exam13.07Oct 8, 2026aa_hle
- 0.29Oct 8, 2026
0 of 10 ranked benchmarks measured
- Terminal-Bench Hard9.09Oct 8, 2026aa_terminalbench_hard
- SciCode39.12Sep 4, 2026aa_scicode
0 of 3 ranked benchmarks measured
- 39.67Oct 8, 2026
0 of 3 ranked benchmarks measured
- IFBench34.01Oct 8, 2026aa_ifbench
0 of 4 ranked benchmarks measured
- AA-Omniscience · Accuracy19.58Oct 8, 2026omniscienceAccuracy
- AA-Omniscience · Non-hallucination12.41Oct 8, 2026omniscienceNonHallucination
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- τ²-Bench Telecom (AA run)26.61Oct 8, 2026aa_tau2
- AA Intelligence10.61Oct 8, 2026aa_intelligence_index
- -50.85Oct 8, 2026
- 19.10Jun 18, 2026
- 19.81Jun 18, 2026
INTELLECT-3: common questions
Who makes INTELLECT-3?
INTELLECT-3 is made by Prime Intellect.
When was INTELLECT-3 released?
INTELLECT-3 was released on Nov 27, 2025, according to Artificial Analysis.
What is INTELLECT-3 good at?
INTELLECT-3 is behind the leaders in agentic tasks and reasoning. Too few results yet to rate coding, safety, long context, math, multimodal tasks, multilingual tasks, instruction following, or factuality.
How much does INTELLECT-3 cost?
INTELLECT-3 costs $0.20 per million input tokens and $1.10 per million output tokens, according to prime-intellect. At a mix of three input tokens to one output token, it is cheaper than 64% of the 330 priced models we track.
How many benchmarks has INTELLECT-3 been tested on?
We track 15 results for INTELLECT-3 on 15 benchmarks from 1 source. The latest was recorded on Oct 8, 2026.
Which API features does INTELLECT-3 support?
OpenRouter lists tool calling, structured outputs, and reasoning for INTELLECT-3.
About this record
Where INTELLECT-3's numbers come from, and every name it appears under.
- Tracked since
- Apr 27, 2026
- Newest source mention
- Apr 27, 2026
Where the results come from
Verification: 15 scores · 0 independently verified · 15 aggregator-attributed. How these tiers are assigned
From 1 source on 1 site. Artificial Analysis supplies all of them. Bars are coloured by trust tier.
- artificialanalysis.ai15