GPT-4o vs Kimi K2 (Non-Reasoning)
Wins 2 of 6 areas
Facts · Long documents
Wins 4 of 6 areas
Coding · Agents · Reasoning · Following instructions
Kimi K2 (Non-Reasoning) is the stronger all-rounder.GPT-4o is better at facts.
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 thinking02Kimi K2 (Non-Reasoning)2 of 3 tests · 1 tie
- CodingWriting and fixing software02Kimi K2 (Non-Reasoning)2 of 2 tests
- AgentsCarrying out multi-step tasks on its own01Kimi K2 (Non-Reasoning)1 of 1 test
- Following instructionsDoing exactly what it is asked01Kimi K2 (Non-Reasoning)1 of 1 test
- FactsGetting facts right instead of making them up21GPT-4o2 of 3 tests
- Long documentsFinding answers in very long texts10GPT-4o1 of 1 test
Agents, 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 (Non-Reasoning) costs 86% 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 (Non-Reasoning) pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+24points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+7.6points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+5.6points ahead
Where GPT-4o pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+38.7points ahead
- Reasons across sets of long documentsAA-LCR+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.
CodingKimi K2 (Non-Reasoning)
- Terminal-Bench HardKimi K2 (Non-Reasoning) by 7.68.315.9+7.6
- SciCodeKimi K2 (Non-Reasoning) by 1.233.334.5+1.2
ReasoningKimi K2 (Non-Reasoning)
- GPQA DiamondKimi K2 (Non-Reasoning) by 2452.676.6+24
- Humanity's Last ExamKimi K2 (Non-Reasoning) by 5.61.87.4+5.6
- CritPttie00tie
FactsGPT-4o
- AA-Omniscience · Non-hallucinationGPT-4o by 38.762.123.4+38.7
- Vectara HHEM hallucination ratelower is betterGPT-4o by 8.39.617.9+8.3
- AA-Omniscience · AccuracyKimi K2 (Non-Reasoning) by 3.723.727.4+3.7
Following instructionsKimi K2 (Non-Reasoning)
- IFBenchKimi K2 (Non-Reasoning) by 5.53641.5+5.5
Other results8 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.
- AA Agentic IndexKimi K2 (Non-Reasoning) by 39.58.447.9+39.5
- τ²-Bench Telecom (AA run)Kimi K2 (Non-Reasoning) by 32.228.961.1+32.2
- vectara_avg_summary_lengthGPT-4o by 27.486.659.2+27.4
- AA-OmniscienceGPT-4o by 17.8-10.5-28.3+17.8
- Artificial Analysis Coding IndexKimi K2 (Non-Reasoning) by 10.624.234.8+10.6
- vectara_factual_consistencyGPT-4o by 8.390.482.1+8.3
- AA IntelligenceKimi K2 (Non-Reasoning) by 5.47.312.7+5.4
- vectara_answer_rateKimi K2 (Non-Reasoning) by 4.893.898.6+4.8
Questions people ask
Which is better, GPT-4o or Kimi K2 (Non-Reasoning)?
Kimi K2 (Non-Reasoning) wins four of the six areas where both have results: coding, agents, reasoning and following instructions. GPT-4o wins facts and long documents.
Which is better for coding?
Kimi K2 (Non-Reasoning). It wins 2 of the 2 coding tests both models report; GPT-4o wins none.
Which is cheaper?
GPT-4o costs $5.00 per million input tokens and $15.00 per million output tokens; Kimi K2 (Non-Reasoning) costs $0.57 and $2.30. That makes Kimi K2 (Non-Reasoning) about 86% 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 11 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 8 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.