o3 vs Kimi K2.6 vs Gemini 2.5 Pro
Too close to call on our weighted score (Kimi K2.6 65, Gemini 2.5 Pro 64, o3 59). The right pick depends on what you value most.
Price in rating: Included · Exclude price
OpenAI
o3
59/100- ECI147.1
- Price$2.00 / $8.00
- Context200K
Moonshot AI
Kimi K2.6
65/100- ECI151.6
- Price$0.95 / $4.00
- Context262K
Google
Gemini 2.5 Pro
64/100- ECI144.9
- Price$1.25 / $10.00
- Context1.05M
Too close to call
It is close. Our weighted score puts them within 1 points (Kimi K2.6 65/100, Gemini 2.5 Pro 64/100, o3 59/100), so choose by what matters most for your work: Kimi K2.6 for raw capability and Gemini 2.5 Pro for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityKimi K2.6Capabilities Index (ECI): Kimi K2.6 151.6 · o3 147.1 · Gemini 2.5 Pro 144.9
- Lowest priceKimi K2.6Kimi K2.6 $1.71 · Gemini 2.5 Pro $3.44 · o3 $3.50 per 1M tokens (3:1 blend)
- Longest contextGemini 2.5 ProGemini 2.5 Pro 1,048,576 · Kimi K2.6 262,144 · o3 200,000 tokens
- Widest inputsGemini 2.5 Proo3: Text, Images, PDFs · Kimi K2.6: Text, Images, Video · Gemini 2.5 Pro: Text, Images, PDFs, Audio, Video
- Self-hostingKimi K2.6Publishes downloadable weights
| Measure | Weight | o3 | Kimi K2.6 | Gemini 2.5 Pro |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 75 | 79 | 73 |
| Price | 25% | 23 | 37 | 23 |
| Inputs & features | 15% | 80 | 80 | 100 |
| Context window | 10% | 39 | 43 | 65 |
| Overall | 100% | 59/100 | 65/100 | 64/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 147.1 | 151.6 (best) | 144.9 |
| ECI rank | #81 of 158 | #61 of 158 (best) | #92 of 158 |
| GPQA DiamondGraduate-level science questions | 81.8% | 90.8% (best) | 85.3% |
| FrontierMath Tiers 1–3Research-level mathematics | 33.3% | 57.2% (best) | 24.6% |
| OTIS Mock AIME 2024–2025Competition mathematics | 84.4% | 96.1% (best) | 84.7% |
| SWE-bench VerifiedFixing real GitHub issues | 62.3% | 76.7% (best) | 57.6% |
| SimpleQA VerifiedShort factual questions | 49.4% (best) | 34.9% | — |
| Price per million tokens | |||
| Input | $2.00 | $0.95 (best) | $1.25 |
| Output | $8.00 | $4.00 (best) | $10.00 |
| Cached input | $0.50 | $0.16 | $0.125 (best) |
| Blended (3:1) | $3.50 | $1.71 (best) | $3.44 |
| Long-context rate | Same rate | Same rate | Over 200K: $2.50 / $15.00 |
| Price source | Official OpenAI API | Official Moonshot AI API | Official Google API |
| Limits | |||
| Context window | 200,000 tokens | 262,144 tokens | 1,048,576 tokens (best) |
| Max output | 100,000 tokens | 262,144 tokens (best) | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | Yes | No | Yes |
| Audio | No | No | Yes |
| Video | No | Yes | Yes |
| Reasoning | Yeslow · medium · high | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | Yes |
| Availability | |||
| Weights | Proprietary | Open | Proprietary |
| API model ID | o3 | kimi-k2.6 | gemini-2.5-pro |
| API providers | 23 | 64 (best) | 31 |
| Released | Apr 16, 2025 | Apr 20, 2026 | Jun 17, 2025 |
| Knowledge cutoff | May 2024 | Jan 2025 | 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.
o3$36.00
Kimi K2.6$17.50
Gemini 2.5 Pro$32.50
Which should you choose?
Which is better: o3, Kimi K2.6 or Gemini 2.5 Pro?
It is close. Our weighted score puts them within 1 points (Kimi K2.6 65/100, Gemini 2.5 Pro 64/100, o3 59/100), so choose by what matters most for your work: Kimi K2.6 for raw capability and Gemini 2.5 Pro for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, o3, Kimi K2.6 or Gemini 2.5 Pro?
Kimi K2.6 is cheaper at $0.95 input / $4.00 output per million tokens (official Moonshot AI API price). Gemini 2.5 Pro costs $1.25 input / $10.00 output per million tokens (official Google API price); 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 $1.71 per million tokens for Kimi K2.6 versus $3.44 for Gemini 2.5 Pro (2× as much) and $3.50 for o3 (2× as much).
Which scores higher on benchmarks?
Kimi K2.6 scores higher on the Capabilities Index (ECI): Kimi K2.6 151.6 (#61 of 158), o3 147.1 (#81 of 158) and Gemini 2.5 Pro 144.9 (#92 of 158). Their confidence ranges do not overlap (149.9–153.4 vs 145.6–148.6), so the gap is a real one. On individual benchmarks: GPQA Diamond — Kimi K2.6 90.8%, Gemini 2.5 Pro 85.3%, o3 81.8%; FrontierMath Tiers 1–3 — Kimi K2.6 57.2%, o3 33.3%, Gemini 2.5 Pro 24.6%; OTIS Mock AIME 2024–2025 — Kimi K2.6 96.1%, Gemini 2.5 Pro 84.7%, o3 84.4%; SWE-bench Verified — Kimi K2.6 76.7%, o3 62.3%, Gemini 2.5 Pro 57.6%.
Which is better for coding?
Kimi K2.6 resolves more real GitHub issues on SWE-bench Verified: Kimi K2.6 76.7%, o3 62.3% and Gemini 2.5 Pro 57.6%. All three support tool calling for agent workflows.
Which has the bigger context window?
Gemini 2.5 Pro has the largest context window at 1,048,576 tokens, against 262,144 for Kimi K2.6 and 200,000 for o3. Maximum output per response: o3 up to 100,000, Kimi K2.6 up to 262,144, Gemini 2.5 Pro up to 65,536 tokens.
Which can read images, PDFs, audio or video?
o3 accepts text, images and PDFs; Kimi K2.6 accepts text, images and video; Gemini 2.5 Pro accepts text, images, PDFs, audio and video. Gemini 2.5 Pro handles the widest range of inputs.
Are any of these open source?
Kimi K2.6 publishes its weights and can be self-hosted; o3 and Gemini 2.5 Pro is proprietary.
Which is newer?
Kimi K2.6 is the newest, released Apr 20, 2026. Gemini 2.5 Pro came out Jun 17, 2025; o3 came out Apr 16, 2025. Knowledge cutoff: o3 May 2024, Kimi K2.6 Jan 2025, Gemini 2.5 Pro 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.