Kimi K2.5 vs Nemotron 3 Ultra 550B A55B
Wins 5 of 7 areas
Coding · Agents · Reasoning · Facts · Math
Wins 2 of 7 areas
Long documents · Following instructions
Kimi K2.5 is the stronger all-rounder.Nemotron 3 Ultra 550B A55B is cheaper and better at following instructions.
Scores updated · 36 tests both models report · How we compare
Where each one wins
Tests won in each of the seven 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.
- ReasoningHard problems that need careful thinking20Kimi K2.52 of 3 tests · 1 tie
- CodingWriting and fixing software43Kimi K2.54 of 7 tests
- AgentsCarrying out multi-step tasks on its own21Kimi K2.52 of 4 tests · 1 tie
- FactsGetting facts right instead of making them up21Kimi K2.52 of 3 tests
- MathCompetition and research-level math21Kimi K2.52 of 3 tests
- Following instructionsDoing exactly what it is asked02Nemotron 3 Ultra 550B A55B2 of 2 tests
- Long documentsFinding answers in very long texts01Nemotron 3 Ultra 550B A55B1 of 2 tests · 1 tie
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.
Nemotron 3 Ultra 550B A55B costs 14% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Kimi K2.5 pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+30.5points ahead
- Multi-step tasks using many real software toolsMCP Atlas+19.1points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+12.6points ahead
Where Nemotron 3 Ultra 550B A55B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+36points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+11.2points ahead
- Olympiad math problems with short answersIMOAnswerBench+10.5points ahead
Every test, side by side
All 36 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingKimi K2.5
- SciCodeKimi K2.5 by 8.74940.3+8.7
- Terminal-Bench 2.1Nemotron 3 Ultra 550B A55B by 8.245.753.9+8.2
- SWE-bench VerifiedKimi K2.5 by 6.176.870.7+6.1
- SWE-bench MultilingualKimi K2.5 by 5.37367.7+5.3
- LiveCodeBench v6Nemotron 3 Ultra 550B A55B by 48589+4
- Terminal-Bench HardNemotron 3 Ultra 550B A55B by 1.634.836.4+1.6
- SWE-bench ProKimi K2.5 by 150.749.7+1
AgentsKimi K2.5
- BrowseCompKimi K2.5 by 30.574.944.4+30.5
- MCP AtlasKimi K2.5 by 19.163.844.7+19.1
- GDPValNemotron 3 Ultra 550B A55B by 8.71725.7+8.7
- τ-Bench V3 · Bankingtie14.214.2tie
ReasoningKimi K2.5
- Humanity's Last ExamKimi K2.5 by 2.330.728.4+2.3
- GPQA DiamondKimi K2.5 by 1.287.986.7+1.2
- CritPttie3.13.1tie
FactsKimi K2.5
- AA-Omniscience · Non-hallucinationNemotron 3 Ultra 550B A55B by 3634.370.3+36
- AA-Omniscience · AccuracyKimi K2.5 by 12.635.222.6+12.6
- SimpleQA VerifiedKimi K2.5 by 1.934.332.4+1.9
MathKimi K2.5
- IMOAnswerBenchNemotron 3 Ultra 550B A55B by 10.581.892.3+10.5
- HMMT Feb. 2026Kimi K2.5 by 8.387.178.8+8.3
- AIME 2026Kimi K2.5 by 1.695.894.2+1.6
Long documentsNemotron 3 Ultra 550B A55B
- AA-LCRNemotron 3 Ultra 550B A55B by 1.37879.3+1.3
- LongBench v2tie6161.9tie
Following instructionsNemotron 3 Ultra 550B A55B
- IFBenchNemotron 3 Ultra 550B A55B by 11.270.281.4+11.2
- Multi-ChallengeNemotron 3 Ultra 550B A55B by 2.461.463.8+2.4
Other results12 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 v2Nemotron 3 Ultra 550B A55B by 155 rating points10091164+155 rating
- HLE (with tools)Kimi K2.5 by 12.850.237.4+12.8
- τ²-Bench Telecom (AA run)Kimi K2.5 by 12.695.983.3+12.6
- AA-OmniscienceNemotron 3 Ultra 550B A55B by 6.9-7.3-0.4+6.9
- SWEBench Pro PublicKimi K2.5 by 4.350.746.4+4.3
- Artificial Analysis Coding IndexNemotron 3 Ultra 550B A55B by 2.546.849.3+2.5
- Global-MMLU-LiteNemotron 3 Ultra 550B A55B by 1.68485.6+1.6
- StrongREJECTtie99.598.7tie
- AA Intelligencetie23.522.9tie
- τ³-Bench Bankingtie14.213.8tie
- MMLU-Protie87.186.8tie
- AA Agentic Indextie21.721.7tie
Questions people ask
Which is better, Kimi K2.5 or Nemotron 3 Ultra 550B A55B?
Kimi K2.5 wins five of the seven areas where both have results: coding, agents, reasoning, facts and math. Nemotron 3 Ultra 550B A55B wins long documents and following instructions, and costs 14% less.
Which is better for coding?
Kimi K2.5. It wins 4 of the 7 coding tests both models report; Nemotron 3 Ultra 550B A55B wins 3.
Which is cheaper?
Kimi K2.5 costs $0.60 per million input tokens and $3.00 per million output tokens; Nemotron 3 Ultra 550B A55B costs $0.60 and $2.50. That makes Nemotron 3 Ultra 550B A55B about 14% cheaper for the same work.
How do you compare the two?
We use the 36 benchmark tests both models have published scores on. The verdict counts the 24 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 12 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.