Kimi K2.6 is the stronger all-rounder.
Scores updated · 11 tests both models report · How we compare
Where each one wins
Tests won in each of the three areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
Agents and reasoning rest on a single test each.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Kimi K2.6 pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+63.5points ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+26.9points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+26.3points ahead
Where Nemotron 3 Super pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 11 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingKimi K2.6
- SWE-bench MultilingualKimi K2.6 by 26.976.749.8+26.9
- Terminal-Bench 2.1Kimi K2.6 by 26.365.939.6+26.3
- SWE-bench VerifiedKimi K2.6 by 17.180.263.1+17.1
- SciCodeKimi K2.6 by 16.451.535.1+16.4
Other results5 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- GDPval-AA v2Kimi K2.6 by 444 rating points1190746+444 rating
- PinchBenchKimi K2.6 by 9.890.280.4+9.8
- τ³-Bench BankingKimi K2.6 by 8.220.612.4+8.2
- MMLU-ProKimi K2.6 by 3.287.183.9+3.2
- AA IntelligenceKimi K2.6 by 12726+1
Questions people ask
Which is better, Kimi K2.6 or Nemotron 3 Super?
Kimi K2.6 wins all three areas where both have results: coding, agents and reasoning. Nemotron 3 Super wins none.
Which is better for coding?
Kimi K2.6. It wins 4 of the 4 coding tests both models report; Nemotron 3 Super wins none.
How do you compare the two?
We use the 11 benchmark tests both models have published scores on. The verdict counts the 6 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 5 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.