GPT-4o vs Kimi K3
Wins 0 of 6 areas
—
Wins 6 of 6 areas
Coding · Agents · Reasoning · Facts · Images and charts · Long documents
Kimi K3 is the stronger all-rounder.
Scores updated · 19 tests both models report · How we compare
Where each one wins
Tests won in each of the six 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 thinking04Kimi K34 of 4 tests
- AgentsCarrying out multi-step tasks on its own02Kimi K32 of 2 tests
- Images and chartsUnderstanding pictures, charts and video02Kimi K32 of 2 tests
- FactsGetting facts right instead of making them up12Kimi K32 of 3 tests
- CodingWriting and fixing software01Kimi K31 of 1 test
- Long documentsFinding answers in very long texts01Kimi K31 of 1 test
Coding and long documents 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 K3 costs 10% 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 K3 pulls ahead
- Completes tasks by operating a computer desktopOSWorld-Verified+79.8points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+45.1points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+40.9points ahead
Where GPT-4o pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+15.3points ahead
Every test, side by side
All 19 tests both models report. The winning score is in its model's colour; marks a score checked independently.
AgentsKimi K3
- OSWorld-VerifiedKimi K3 by 79.8584.8+79.8
- GDPValKimi K3 by 51.7051.7+51.7
ReasoningKimi K3
- ARC-AGI-2Kimi K3 by 60.4060.4+60.4
- Humanity's Last ExamKimi K3 by 45.11.846.9+45.1
- GPQA DiamondKimi K3 by 40.952.693.5+40.9
- CritPtKimi K3 by 23.4023.4+23.4
FactsKimi K3
- SimpleQA VerifiedKimi K3 by 24.62650.6+24.6
- AA-Omniscience · AccuracyKimi K3 by 23.923.747.6+23.9
- AA-Omniscience · Non-hallucinationGPT-4o by 15.362.146.8+15.3
Images and chartsKimi K3
- CharXiv (RQ)Kimi K3 by 32.558.891.3+32.5
- MMMU-ProKimi K3 by 24.256.380.5+24.2
Other results6 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.
- ARC-AGI-1Kimi K3 by 904.594.5+90
- MATH-VisionKimi K3 by 67.430.497.8+67.4
- Artificial Analysis Coding IndexKimi K3 by 5224.276.2+52
- AA Agentic IndexKimi K3 by 42.28.450.6+42.2
- AA IntelligenceKimi K3 by 36.37.343.6+36.3
- AA-OmniscienceKimi K3 by 30.2-10.519.7+30.2
Questions people ask
Which is better, GPT-4o or Kimi K3?
Kimi K3 wins all six areas where both have results: coding, agents, reasoning, facts, images and charts and long documents. GPT-4o wins none.
Which is better for coding?
Kimi K3. It wins the one coding test both models report.
Which is cheaper?
GPT-4o costs $5.00 per million input tokens and $15.00 per million output tokens; Kimi K3 costs $3.00 and $15.00. That makes Kimi K3 about 10% cheaper for the same work.
How do you compare the two?
We use the 19 benchmark tests both models have published scores on. The verdict counts the 13 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 6 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.