GPT-4.1 vs Kimi K2 (Non-Reasoning)
Wins 2 of 6 areas
Long documents · Following instructions
Wins 2 of 6 areas
Agents · Reasoning
The two are evenly matched.GPT-4.1 is better at long documents and following instructions; Kimi K2 (Non-Reasoning) at reasoning and agents.
Scores updated · 20 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 4 tests · 2 ties
- AgentsCarrying out multi-step tasks on its own01Kimi K2 (Non-Reasoning)1 of 1 test
- Long documentsFinding answers in very long texts10GPT-4.11 of 1 test
- Following instructionsDoing exactly what it is asked10GPT-4.11 of 1 test
- CodingWriting and fixing software11Even1 each
- FactsGetting facts right instead of making them up11Even1 each · 1 tie
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 71% 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 (Non-Reasoning) pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+16.7points ahead
- Real work tasks from 44 professionsGDPVal+10.8points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+10points ahead
Every test, side by side
All 20 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingEven
- SciCodeGPT-4.1 by 3.638.134.5+3.6
- Terminal-Bench HardKimi K2 (Non-Reasoning) by 2.313.615.9+2.3
ReasoningKimi K2 (Non-Reasoning)
- GPQA DiamondKimi K2 (Non-Reasoning) by 1066.676.6+10
- Humanity's Last ExamKimi K2 (Non-Reasoning) by 3.24.27.4+3.2
- SimpleBenchtie2726.3tie
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationKimi K2 (Non-Reasoning) by 16.76.723.4+16.7
- Vectara HHEM hallucination ratelower is betterGPT-4.1 by 12.35.617.9+12.3
- AA-Omniscience · Accuracytie27.827.4tie
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.
- vectara_avg_summary_lengthGPT-4.1 by 32.591.759.2+32.5
- AA Agentic IndexKimi K2 (Non-Reasoning) by 20.627.347.9+20.6
- τ²-Bench Telecom (AA run)Kimi K2 (Non-Reasoning) by 1447.161.1+14
- Artificial Analysis Coding IndexKimi K2 (Non-Reasoning) by 1321.834.8+13
- vectara_factual_consistencyGPT-4.1 by 12.394.482.1+12.3
- AA-OmniscienceKimi K2 (Non-Reasoning) by 11.3-39.6-28.3+11.3
- vectara_answer_rateGPT-4.1 by 1.399.998.6+1.3
- AA Intelligencetie12.712.7tie
Questions people ask
Which is better, GPT-4.1 or Kimi K2 (Non-Reasoning)?
GPT-4.1 and Kimi K2 (Non-Reasoning) each win two of the six areas where both have results. GPT-4.1 wins long documents and following instructions; Kimi K2 (Non-Reasoning) wins agents and reasoning. Kimi K2 (Non-Reasoning) costs 71% less. They are level on coding and facts.
Which is better for coding?
Neither. They win 1 coding test each of the 2 both models report.
Which is cheaper?
GPT-4.1 costs $2.00 per million input tokens and $8.00 per million output tokens; Kimi K2 (Non-Reasoning) costs $0.57 and $2.30. That makes Kimi K2 (Non-Reasoning) about 71% cheaper for the same work.
How do you compare the two?
We use the 20 benchmark tests both models have published scores on. The verdict counts the 12 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.