Compare · ModelsLive · 2 picked · head to head
Gemini 1.5 Flash (May 2024) vs Kimi K2.6
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Kimi K2.6 wins on 6/6 benchmarks
Kimi K2.6 wins 6 of 6 shared benchmarks. Leads in arena · general · math.
Category leads
arena·Kimi K2.6general·Kimi K2.6math·Kimi K2.6knowledge·Kimi K2.6coding·Kimi K2.6
Hype vs Reality
Attention vs performance
Gemini 1.5 Flash (May 2024)
#165 by perf·no signal
Kimi K2.6
#217 by perf·#15 by attention
Best value
Kimi K2.6
Gemini 1.5 Flash (May 2024)
n/a
no price
Kimi K2.6
18.9 pts/$
$2.03/M
Vendor risk
Who is behind the model
Google DeepMind
$3.53T·Tier 1
Moonshot AI
$50.0B·Tier 1
Head to head
6 benchmarks · 2 models
Gemini 1.5 Flash (May 2024)Kimi K2.6
Chatbot Arena Elo · Overall
Kimi K2.6 leads by +174.5
Gemini 1.5 Flash (May 2024)
1286.5
Kimi K2.6
1461.0
Dtbench
Kimi K2.6 leads by +65.9
Gemini 1.5 Flash (May 2024)
19.0
Kimi K2.6
84.9
FrontierMath-2025-02-28-Private
Kimi K2.6 leads by +39.0
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
Gemini 1.5 Flash (May 2024)
0.0
Kimi K2.6
39.0
GPQA diamond
Kimi K2.6 leads by +70.0
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Gemini 1.5 Flash (May 2024)
21.4
Kimi K2.6
91.4
OTIS Mock AIME 2024-2025
Kimi K2.6 leads by +92.3
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Gemini 1.5 Flash (May 2024)
3.8
Kimi K2.6
96.1
WeirdML
Kimi K2.6 leads by +31.0
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Gemini 1.5 Flash (May 2024)
24.9
Kimi K2.6
55.9
Full benchmark table
| Benchmark | Gemini 1.5 Flash (May 2024) | Kimi K2.6 |
|---|---|---|
Chatbot Arena Elo · Overall | 1286.5 | 1461.0 |
Dtbench | 19.0 | 84.9 |
FrontierMath-2025-02-28-Private FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning. | 0.0 | 39.0 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 21.4 | 91.4 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 3.8 | 96.1 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 24.9 | 55.9 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| n/a | n/a | n/a | n/a | |
| $0.65 | $3.41 | 262K tokens (~131 books) | $13.40 |