Cohereopen-weight
Released: 2026-06-09Artificial AnalysisNorth Mini Code
North Mini Code from Cohere, tracked on the Artificial Analysis Intelligence Index.
Intelligence Index
3.4/ 100
Artificial Analysis Intelligence Index (independent composite)Throughput Speed
171tok/sec
Output streaming throughputTime to First Answer
5.5s
Time to first answer token, including any thinkingCost to Run the Index
0.00USD
Artificial Analysis cost of the full Index runMeasured results · Artificial Analysis
Independent evaluations of North Mini Code. Values are reported as published; nothing here is estimated or derived. Snapshot 2026-11-15.
- Intelligence Index
- 3.4
- Cost to run the Index
- $0.00
- Time per task
- 2.9 min
- Omniscience index
- -49.8
- Reasoning model
- Yes
- Cached-input price
- —
Reasoning & knowledge
- AA-Omniscience Accuracy18.4%
- CritPt0.3%
- CritPt v2 (Hard)1.0%
- GPQA Diamond75.7%
- HLE-Diamond4.2%
- Humanity's Last Exam11.1%
- IFBench57.6%
Coding & terminal agents
- FrontierCode-AA 2.00.2%
- SciCode38.8%
- Terminal-Bench 2.135.6%
- Terminal-Bench 4.00.5%
- Terminal-Bench Hard31.1%
- Terminal-Bench-Science 0.10.0%
Agentic work
- AA-Briefcase v1.1 (Elo)213 Elo
- AutomationBench-AA1.5%
- GDPval-AA (normalized Elo)318 Elo
- τ²-Bench Telecom37.4%
- τ³-Banking6.4%
Long context & documents
Health & safety
Headline Evaluation Breakdown
Six independently measured evaluations (Artificial Analysis)Reasoning · CritPt v2 (Hard)1.0%
Coding & agents · Terminal-Bench 4.00.5%
Long context · AA-LCR37.3%
Knowledge · Humanity's Last Exam11.1%
Instruction following · IFBench57.6%
Sourced Benchmark Evaluations (20)
Verified performance across authoritative benchmarks with provenance tracking.| Benchmark | Status | Score | Trust | Date | Source Type | Provenance |
|---|---|---|---|---|---|---|
| AA-LCR (Long Context Reasoning) | Active | 37.3% | 93 | 2026-11-15 | independent | Source ↗ |
| AutomationBench-AA | Active | 1.5% | 93 | 2026-11-15 | independent | Source ↗ |
| MLCR-AA (Medical Long Context Reasoning) | Active | 4.4% | 93 | 2026-11-15 | independent | Source ↗ |
| GDP.pdf | Active | 1.8% | 93 | 2026-11-15 | independent | Source ↗ |
| FrontierCode-AA 2.0 | Active | 0.2% | 93 | 2026-11-15 | independent | Source ↗ |
| AA-Omniscience (Non-Hallucination) | Active | 16.5% | 93 | 2026-11-15 | independent | Source ↗ |
| AA-Omniscience (Accuracy) | Active | 18.4% | 93 | 2026-11-15 | independent | Source ↗ |
| HLE-Diamond | Active | 4.2% | 93 | 2026-11-15 | independent | Source ↗ |
| CritPt v2 (Hard) | Active | 1% | 93 | 2026-11-15 | independent | Source ↗ |
| CritPt | Active | 0.3% | 93 | 2026-11-15 | independent | Source ↗ |
| GPQA | Nearing Saturation | 75.7% | 78 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench-Science 0.1 | Active | 0% | 93 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench 4.0 | Active | 0.5% | 93 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench 2.1 | Active | 35.6% | 93 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench Hard | Active | 31.1% | 93 | 2026-11-15 | independent | Source ↗ |
| τ³-Banking | Active | 6.4% | 93 | 2026-11-15 | independent | Source ↗ |
| τ²-Bench Telecom | Active | 37.4% | 93 | 2026-11-15 | independent | Source ↗ |
| SciCode | Active | 38.8% | 93 | 2026-11-15 | independent | Source ↗ |
| IFBench | Active | 57.6% | 93 | 2026-11-15 | independent | Source ↗ |
| Humanity's Last Exam | Active | 11.1% | 93 | 2026-11-15 | independent | Source ↗ |
Local Hardware Execution (Ollama)Hardware Compatible
# 1. Pull and execute model locally with Ollama
ollama run cohere-north-mini-code
# 2. Or invoke via local OpenAI-compatible endpoint
curl http://localhost:11434/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "cohere-north-mini-code",
"messages": [{"role": "user", "content": "Analyze reasoning chains on AIME 2026"}]
}'Evaluation & Sourcing Notes
Scores listed for North Mini Code represent verified evaluations extracted from official research papers, independent evaluation suites (HELM, LMSYS, OpenCompass, LiveBench), and verified audit reports.
All benchmarks marked as saturated or deprecated reflect historical performance where the benchmark no longer provides active discriminative power.