Kimi K2 Instruct vs o3 vs Gemini 2.5 Flash Preview 05-20
Gemini 2.5 Flash Preview 05-20 comes out ahead, 67 to 59 and 53 on our weighted score, and it is the cheaper option too.
Price in rating: Included · Exclude price
Moonshot AI
Kimi K2 Instruct
53/100- ECI141.3
- Price$0.57 / $2.30
- Context131K
OpenAI
o3
59/100- ECI147.1
- Price$2.00 / $8.00
- Context200K
- Our pick
Google
Gemini 2.5 Flash Preview 05-20
67/100- ECI141.6
- Price$0.142 / $3.33
- Context1.05M
Gemini 2.5 Flash Preview 05-20 is our pick
Gemini 2.5 Flash Preview 05-20 is the better all-round choice, scoring 67/100 against o3 (59) and Kimi K2 Instruct (53). It leads on inputs & features and context window. o3 wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- Capabilityo3Capabilities Index (ECI): o3 147.1 · Gemini 2.5 Flash Preview 05-20 141.6 · Kimi K2 Instruct 141.3
- Lowest priceGemini 2.5 Flash Preview 05-20Gemini 2.5 Flash Preview 05-20 $0.938 · Kimi K2 Instruct $1.00 · o3 $3.50 per 1M tokens (3:1 blend)
- Longest contextGemini 2.5 Flash Preview 05-20Gemini 2.5 Flash Preview 05-20 1,048,576 · o3 200,000 · Kimi K2 Instruct 131,072 tokens
- Widest inputsGemini 2.5 Flash Preview 05-20Kimi K2 Instruct: Text · o3: Text, Images, PDFs · Gemini 2.5 Flash Preview 05-20: Text, Images, PDFs, Audio, Video
- Self-hostingKimi K2 InstructPublishes downloadable weights (Modified MIT)
| Measure | Weight | Kimi K2 Instruct | o3 | Gemini 2.5 Flash Preview 05-20 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 69 | 75 | 69 |
| Price | 25% | 48 | 23 | 49 |
| Inputs & features | 15% | 25 | 80 | 90 |
| Context window | 10% | 32 | 39 | 65 |
| Overall | 100% | 53/100 | 59/100 | 67/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 141.3 | 147.1 (best) | 141.6 |
| ECI rank | #108 of 158 | #81 of 158 (best) | #106 of 158 |
| GPQA DiamondGraduate-level science questions | — | 81.8% | — |
| FrontierMath Tiers 1–3Research-level mathematics | — | 33.3% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 84.4% (best) | 70.8% |
| SWE-bench VerifiedFixing real GitHub issues | — | 62.3% | — |
| SimpleQA VerifiedShort factual questions | — | 49.4% | — |
| Price per million tokens | |||
| Input | $0.57 | $2.00 | $0.142 (best) |
| Output | $2.30 (best) | $8.00 | $3.33 |
| Cached input | — | $0.50 | — |
| Blended (3:1) | $1.00 | $3.50 | $0.938 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 11 providers | Official OpenAI API | Median of 1 providers |
| Limits | |||
| Context window | 131,072 tokens | 200,000 tokens | 1,048,576 tokens (best) |
| Max output | 32,768 tokens | 100,000 tokens (best) | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | Yes | Yes |
| Audio | No | No | Yes |
| Video | No | No | Yes |
| Reasoning | No | Yeslow · medium · high | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | OpenModified MIT | Proprietary | Proprietary |
| API model ID | — | o3 | — |
| API providers | 11 | 23 (best) | 1 |
| Released | Jul 11, 2025 | Apr 16, 2025 | May 20, 2025 |
| Knowledge cutoff | — | May 2024 | Jan 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Kimi K2 Instruct$10.30
o3$36.00
Gemini 2.5 Flash Preview 05-20$8.07
Which should you choose?
Which is better: Kimi K2 Instruct, o3 or Gemini 2.5 Flash Preview 05-20?
Gemini 2.5 Flash Preview 05-20 is the better all-round choice, scoring 67/100 against o3 (59) and Kimi K2 Instruct (53). It leads on inputs & features and context window. o3 wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, Kimi K2 Instruct, o3 or Gemini 2.5 Flash Preview 05-20?
Gemini 2.5 Flash Preview 05-20 is cheaper at $0.142 input / $3.33 output per million tokens (median across 1 API provider). Kimi K2 Instruct costs $0.57 input / $2.30 output per million tokens (median across 11 API providers); o3 costs $2.00 input / $8.00 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $0.938 per million tokens for Gemini 2.5 Flash Preview 05-20 versus $1.00 for Kimi K2 Instruct (1.1× as much) and $3.50 for o3 (3.7× as much).
Which scores higher on benchmarks?
o3 scores higher on the Capabilities Index (ECI): o3 147.1 (#81 of 158), Gemini 2.5 Flash Preview 05-20 141.6 (#106 of 158) and Kimi K2 Instruct 141.3 (#108 of 158). Their confidence ranges do not overlap (145.6–148.6 vs 139.4–143.6), so the gap is a real one.
Which is better for coding?
There are no published SWE-bench Verified results for Kimi K2 Instruct and Gemini 2.5 Flash Preview 05-20 yet, so there is no like-for-like coding score. On overall capability, o3 leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.
Which has the bigger context window?
Gemini 2.5 Flash Preview 05-20 has the largest context window at 1,048,576 tokens, against 200,000 for o3 and 131,072 for Kimi K2 Instruct. Maximum output per response: Kimi K2 Instruct up to 32,768, o3 up to 100,000, Gemini 2.5 Flash Preview 05-20 up to 65,536 tokens.
Which can read images, PDFs, audio or video?
Kimi K2 Instruct accepts text; o3 accepts text, images and PDFs; Gemini 2.5 Flash Preview 05-20 accepts text, images, PDFs, audio and video. Gemini 2.5 Flash Preview 05-20 handles the widest range of inputs.
Are any of these open source?
Kimi K2 Instruct publishes its weights (Modified MIT) and can be self-hosted; o3 and Gemini 2.5 Flash Preview 05-20 is proprietary.
Which is newer?
Kimi K2 Instruct is the newest, released Jul 11, 2025. Gemini 2.5 Flash Preview 05-20 came out May 20, 2025; o3 came out Apr 16, 2025. Knowledge cutoff: o3 May 2024, Gemini 2.5 Flash Preview 05-20 Jan 2025.
How do you decide the winner?
This rating uses capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 18, 2026.