Prime IntellectIntellect 3
Intellect 3 is a Prime Intellect open-weights reasoning model, released 27 Nov 2025. Its best configuration ranks #485 of 785 on the BenchLeader Index at 46.5 ±4.0, in the lower half. The ± is the point: 302 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in maths (55) and lowest in instruction following (38). Last measured 22 Oct 2026.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- 131k
- Full answer
- –
- Cost per run
- –
- Released
- 27 Nov 2025
- Overall index47
- Reasoning45
- Coding54
- Agents & tools42
- Maths55
- Knowledge39
- Instruction following38
- Human preference52
- Long context44
- Composite41
Versions
Prime Intellect has shipped 2 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| Intellect 3this page | 27 Nov 2025 | 46.5 | #485 |
| INTELLECT-1 | 29 Nov 2024 | – | – |
How its index has moved
9 Sept 2026 to 19 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Metadata
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA Openness Indexnot in index | 72.2#21 | Artificial Analysis |
Reasoning
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Hard Prompts | 1375#191 | Arena (LMArena) | |
| GPQA Diamond (AA)not in index | 76.1%#240 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 13.1%#275 | Artificial Analysis | |
| CritPt | 0.3%#271 | Artificial Analysis |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Coding | 1415#184 | Arena (LMArena) |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Terminal-Bench Hard | 9.1%#231 | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | 26.6%#280 | Artificial Analysis |
Maths
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Maths | 1373#178 | Arena (LMArena) |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-Omniscience | -50.9#397 | Artificial Analysis | |
| AA-Omniscience: accuracynot in index | 19.6%#313 | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 12.4%#375 | Artificial Analysis | |
| Global-MMLU-Lite (AA)not in index | 80.3%#27 | Artificial Analysis |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| IFBench | 34.0%#323 | Artificial Analysis | |
| Arena Instruction Followingnot in index | 1332#204 | Arena (LMArena) |
Human preference
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Text | 1356#195 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1308#206 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1356#192 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1353#201 | Arena (LMArena) |
Long context
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-LCR | 39.7%#359 | Artificial Analysis |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA Intelligence Index v4.3.2 | 10.6#374 | Artificial Analysis |
See also
Questions people ask
- What are Intellect 3's benchmark scores?
- As of 25 Oct 2026, Intellect 3 scores 46.5 ±4.0 on the BenchLeader Index, strongest in maths (55) and weakest in instruction following (38). That rests on 10 independent benchmark results, and every score on this page links to its publisher.
- How does Intellect 3 rank?
- Intellect 3 is #485 of 785 ranked configurations on 25 Oct 2026. 302 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- When was Intellect 3 released?
- Prime Intellect released Intellect 3 on 27 Nov 2025.
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Intellect 3: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/intellect-3.