command-r7B-12-2024 — benchmark results

Cohere Command R7B December 2024 open-weight model for efficient retrieval-augmented chat. Provider: Cohere. Released 2024-12-11. Access: Open.

Unified ELO 1384 ± 47, rank #1296 of 1776 rated models, from 22 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Konkur 1404 - Experimental Sciences34.78Accuracy (%, text-only)47.4
SWE-Arena998Elo Score34.7
Konkur 1404 - Humanities32.8Accuracy (%, text-only)26.3
BLUEX v25.41Score (self-reported)22.2
Konkur 1404 - Overall31.55Accuracy (%, text-only)21.1
GSMA Open-Telco - TeleLogs12Score (%)20.9
Konkur 1404 - Foreign Language30.77Accuracy (%, text-only)15.8
GSMA Open-Telco - srsRAN-Bench72Score (%)15.1
GSMA Open-Telco - ORAN-Bench63.33Score (%)14
Context Arena MRCR (2-needle)3.4AUC@1M (%)13.7
Konkur 1404 - Art35.63Accuracy (%, text-only)13.2
SnakeBench13.5TrueSkill Rating13.2

Interactive version: theaggregate.ai/model?slug=command-r7b-12-2024 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.