Apriel-v1.6-15B-Thinker
Apriel-v1.6-15B-Thinker is behind the leaders in instruction following, long context, and reasoning. Too few results yet to rate coding, agentic tasks, safety, math, multimodal tasks, multilingual tasks, 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, Agentic, Safety, Math, Multimodal, Multilingual or Factuality.
Price
No current price is tracked for this model. See the rate card
Evidence
12results on12benchmarks
- 12 aggregator
From 1 source · latest Oct 8, 2026 · How verification works
Apriel-v1.6-15B-Thinker benchmark results
12 results on 12 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
29.2% behind the leader1 of 3 ranked benchmarks measured
- IFBench69.12Oct 8, 2026aa_ifbench
36.4% behind the leader1 of 3 ranked benchmarks measured
- 50.33Aug 10, 2026
44.3% behind the leader3 of 6 ranked benchmarks measured
- GPQA Diamond73.33Oct 8, 2026gpqa
- Humanity's Last Exam10.80Oct 8, 2026aa_hle
- 0.29Oct 8, 2026
0 of 10 ranked benchmarks measured
- Terminal-Bench Hard14.39Oct 8, 2026aa_terminalbench_hard
- SciCode37.27Sep 4, 2026aa_scicode
0 of 4 ranked benchmarks measured
- AA-Omniscience · Accuracy16.97Oct 8, 2026omniscienceAccuracy
- AA-Omniscience · Non-hallucination8.07Oct 8, 2026omniscienceNonHallucination
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- τ²-Bench Telecom (AA run)69.30Oct 8, 2026aa_tau2
- AA Intelligence13.40Oct 8, 2026aa_intelligence_index
- -59.37Oct 8, 2026
Apriel-v1.6-15B-Thinker: common questions
Who makes Apriel-v1.6-15B-Thinker?
Apriel-v1.6-15B-Thinker is made by ServiceNow.
When was Apriel-v1.6-15B-Thinker released?
Apriel-v1.6-15B-Thinker was released on Nov 25, 2025, according to Artificial Analysis.
What is Apriel-v1.6-15B-Thinker good at?
Apriel-v1.6-15B-Thinker is behind the leaders in instruction following, long context, and reasoning. Too few results yet to rate coding, agentic tasks, safety, math, multimodal tasks, multilingual tasks, or factuality.
How many benchmarks has Apriel-v1.6-15B-Thinker been tested on?
We track 12 results for Apriel-v1.6-15B-Thinker on 12 benchmarks from 1 source. The latest was recorded on Oct 8, 2026.
About this record
Where Apriel-v1.6-15B-Thinker's numbers come from, and every name it appears under.
- Tracked since
- Jul 3, 2026
- Newest source mention
- Jul 3, 2026
Where the results come from
Verification: 12 scores · 0 independently verified · 12 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.ai12