Kimi K3 is the stronger all-rounder.
Scores updated · 10 tests both models report · How we compare
Where each one wins
Tests won in each of the one area 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 rests on a single test.
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 K3 pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+1points ahead
Where Inkling-2-Small-MXFP8 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 10 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results9 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.
- JobBenchInkling-2-Small-MXFP8 by 17.670.552.9+17.6
- GDPval-AA 2.1Inkling-2-Small-MXFP8 by 87 rating points16301543+87 rating
- DAYJOB (Finance)Inkling-2-Small-MXFP8 by 8.313.85.5+8.3
- DAYJOB (Healthcare)Inkling-2-Small-MXFP8 by 7.211.24+7.2
- DeepSearchQA (F1)Kimi K3 by 4.190.995+4.1
- DeepSWE 1.1Inkling-2-Small-MXFP8 by 3.172.169+3.1
- Terminal-Bench-Science 0.1Kimi K3 by 2.45.78.1+2.4
- SWEBench Pro v2 (Hard)Kimi K3 by 1.986.388.2+1.9
- PostTrain Bench v1.2tie31.931.5tie
Questions people ask
Which is better, Inkling-2-Small-MXFP8 or Kimi K3?
Kimi K3 wins the one area where both have results: agents. Inkling-2-Small-MXFP8 wins none.
How do you compare the two?
We use the 10 benchmark tests both models have published scores on. The verdict counts the 1 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 9 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.