GPT-5 vs Kimi K2.6
Wins 0 of 8 areas
—
Wins 7 of 8 areas
Coding · Agents · Reasoning · Images and charts · Math · Long documents · Following instructions
Kimi K2.6 is the stronger all-rounder.
Scores updated · 40 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- CodingWriting and fixing software08Kimi K2.68 of 8 tests
- AgentsCarrying out multi-step tasks on its own03Kimi K2.63 of 3 tests
- ReasoningHard problems that need careful thinking03Kimi K2.63 of 3 tests
- Images and chartsUnderstanding pictures, charts and video03Kimi K2.63 of 3 tests
- MathCompetition and research-level math03Kimi K2.63 of 3 tests
- Long documentsFinding answers in very long texts01Kimi K2.61 of 1 test
- Following instructionsDoing exactly what it is asked01Kimi K2.61 of 1 test
- FactsGetting facts right instead of making them up22Even2 each
Long documents and following instructions 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.
Kimi K2.6 costs 56% less for the same work.
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
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+41.7points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+31.4points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+30.7points ahead
Where GPT-5 pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+15.2points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+7.7points ahead
Every test, side by side
All 40 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingKimi K2.6
- Terminal-Bench 2.1Kimi K2.6 by 30.735.265.9+30.7
- SWE-bench MultilingualKimi K2.6 by 21.455.376.7+21.4
- SWE-bench ProKimi K2.6 by 16.841.858.6+16.8
- Terminal-Bench HardKimi K2.6 by 11.332.643.9+11.3
- LMArena · WebDevKimi K2.6 by 91 rating points14181509+91 rating
- SciCodeKimi K2.6 by 8.642.951.5+8.6
- SWE-bench VerifiedKimi K2.6 by 5.374.980.2+5.3
- LiveCodeBench v6Kimi K2.6 by 2.68789.6+2.6
AgentsKimi K2.6
- BrowseCompKimi K2.6 by 31.454.986.3+31.4
- GDPValKimi K2.6 by 62127+6
- τ-Bench V3 · BankingKimi K2.6 by 1.222.123.3+1.2
ReasoningKimi K2.6
- Humanity's Last ExamKimi K2.6 by 928.537.5+9
- GPQA DiamondKimi K2.6 by 5.785.491.1+5.7
- CritPtKimi K2.6 by 2.35.78+2.3
FactsEven
- AA-Omniscience · Non-hallucinationKimi K2.6 by 41.717.859.5+41.7
- SimpleQA VerifiedGPT-5 by 15.250.134.9+15.2
- AA-Omniscience · AccuracyGPT-5 by 7.740.332.6+7.7
- Vectara HHEM hallucination ratelower is betterKimi K2.6 by 4.315.110.8+4.3
Images and chartsKimi K2.6
- LMArena · VisionKimi K2.6 by 74 rating points12081282+74 rating
- CharXiv (RQ)Kimi K2.6 by 5.681.186.7+5.6
- MMMU-ProKimi K2.6 by 5.274.279.4+5.2
MathKimi K2.6
- IMOAnswerBenchKimi K2.6 by 107686+10
- FrontierMath Tier 4Kimi K2.6 by 3.621.925.6+3.6
- FrontierMath Tiers 1-3 (v2)Kimi K2.6 by 1.855.457.2+1.8
Other results14 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.
- Terminal-Bench 2.0Kimi K2.6 by 31.535.266.7+31.5
- Artificial Analysis Coding IndexKimi K2.6 by 2437.861.8+24
- HLE (with tools)Kimi K2.6 by 18.835.254+18.8
- AA-OmniscienceKimi K2.6 by 14-8.75.3+14
- τ²-Bench Telecom (AA run)Kimi K2.6 by 11.184.895.9+11.1
- LiveCodeBenchKimi K2.6 by 6.183.589.6+6.1
- GPQA (unspecified)Kimi K2.6 by 5.385.791+5.3
- vectara_avg_summary_lengthGPT-5 by 46 rating points162.7116.7+46 rating
- AA Agentic IndexGPT-5 by 4.426.522.1+4.4
- vectara_factual_consistencyKimi K2.6 by 4.384.989.2+4.3
- AA IntelligenceKimi K2.6 by 42327+4
- frontiermath_tier_4_v1Kimi K2.6 by 2.112.514.6+2.1
- vectara_answer_ratetie99.999.7tie
- MMLU-Protie87.187.1tie
Questions people ask
Which is better, GPT-5 or Kimi K2.6?
Kimi K2.6 wins seven of the eight areas we test: coding, agents, reasoning, images and charts, math, long documents and following instructions. GPT-5 wins none. They are level on facts.
Which is better for coding?
Kimi K2.6. It wins 8 of the 8 coding tests both models report; GPT-5 wins none.
Which is cheaper?
GPT-5 costs $1.25 per million input tokens and $10.00 per million output tokens; Kimi K2.6 costs $0.95 and $4.00. That makes Kimi K2.6 about 56% cheaper for the same work.
How do you compare the two?
We use the 40 benchmark tests both models have published scores on. The verdict counts the 26 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 14 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.