Claude Opus 4.6 vs Kimi K3 vs Gemini 3.1 Pro Preview
Too close to call on our weighted score (Gemini 3.1 Pro Preview 68, Kimi K3 65, Claude Opus 4.6 61). The right pick depends on what you value most.
AnthropicClaude Opus 4.6
61/100- ECI155.3
- Price$5.00 / $25.00
- Context1M
Moonshot AIKimi K3
65/100- ECI157.6
- Price$3.00 / $15.00
- Context1.05M
GoogleGemini 3.1 Pro Preview
68/100- ECI154.8
- Price$2.00 / $12.00
- Context1.05M
Too close to call
It is close. Our weighted score puts them within 3 points (Gemini 3.1 Pro Preview 68/100, Kimi K3 65/100, Claude Opus 4.6 61/100), so choose by what matters most for your work: Kimi K3 for raw capability and Gemini 3.1 Pro Preview on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityKimi K3Capabilities Index (ECI): Kimi K3 157.6 · Claude Opus 4.6 155.3 · Gemini 3.1 Pro Preview 154.8
- Lowest priceGemini 3.1 Pro PreviewGemini 3.1 Pro Preview $4.50 · Kimi K3 $6.00 · Claude Opus 4.6 $10.00 per 1M tokens (3:1 blend)
- Longest contextKimi K3 and Gemini 3.1 Pro PreviewKimi K3 1,048,576 · Gemini 3.1 Pro Preview 1,048,576 · Claude Opus 4.6 1,000,000 tokens
- Widest inputsGemini 3.1 Pro PreviewClaude Opus 4.6: Text, Images, PDFs · Kimi K3: Text, Images, Video · Gemini 3.1 Pro Preview: Text, Images, PDFs, Audio, Video
- Self-hostingKimi K3Publishes downloadable weights
| Measure | Weight | Claude Opus 4.6 | Kimi K3 | Gemini 3.1 Pro Preview |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 85 | 88 | 84 |
| Price | 25% | 2 | 13 | 19 |
| Inputs & features | 15% | 80 | 80 | 100 |
| Context window | 10% | 60 | 61 | 61 |
| Overall | 100% | 61/100 | 65/100 | 68/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Claude Opus 4.6Anthropic | Kimi K3Moonshot AI | Gemini 3.1 Pro PreviewGoogle |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 155.3 | 157.6 (best) | 154.8 |
| ECI rank | #27 of 148 | #13 of 148 (best) | #31 of 148 |
| GPQA DiamondGraduate-level science questions | 90.5% | 93.1% | 94.4% (best) |
| FrontierMath Tiers 1–3Research-level mathematics | 66.0% | 72.2% (best) | 59.7% |
| OTIS Mock AIME 2024–2025Competition mathematics | 94.4% | 97.2% (best) | 95.6% |
| SWE-bench VerifiedFixing real GitHub issues | 78.7% (best) | — | 75.6% |
| SimpleQA VerifiedShort factual questions | 47.0% | 50.6% | 73.5% (best) |
| Price per million tokens | |||
| Input | $5.00 | $3.00 | $2.00 (best) |
| Output | $25.00 | $15.00 | $12.00 (best) |
| Cached input | $0.50 | $0.30 | $0.20 (best) |
| Blended (3:1) | $10.00 | $6.00 | $4.50 (best) |
| Long-context rate | Same rate | Same rate | Over 200K: $4.00 / $18.00 |
| Price source | Official Anthropic API | Official Moonshot AI API | Official Google API |
| Limits | |||
| Context window | 1,000,000 tokens | 1,048,576 tokens (best) | 1,048,576 tokens (best) |
| Max output | 128,000 tokens | 131,072 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 · max | Yeslow · high · max | Yeslow · medium · high |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | Yes |
| Availability | |||
| Weights | Proprietary | Open | Proprietary |
| API model ID | claude-opus-4-6 | kimi-k3 | gemini-3.1-pro-preview |
| API providers | 33 | 68 (best) | 26 |
| Released | Feb 5, 2026 | Jul 16, 2026 | Feb 19, 2026 |
| Knowledge cutoff | May 31, 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.
- Claude Opus 4.6$100.00
- Kimi K3$60.00
- Gemini 3.1 Pro Preview$44.00
Which should you choose?
Which is better: Claude Opus 4.6, Kimi K3 or Gemini 3.1 Pro Preview?
It is close. Our weighted score puts them within 3 points (Gemini 3.1 Pro Preview 68/100, Kimi K3 65/100, Claude Opus 4.6 61/100), so choose by what matters most for your work: Kimi K3 for raw capability and Gemini 3.1 Pro Preview on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, Claude Opus 4.6, Kimi K3 or Gemini 3.1 Pro Preview?
Gemini 3.1 Pro Preview is cheaper at $2.00 input / $12.00 output per million tokens (official Google API price). Kimi K3 costs $3.00 input / $15.00 output per million tokens (official Moonshot AI API price); Claude Opus 4.6 costs $5.00 input / $25.00 output per million tokens (official Anthropic API price). At a typical mix of three input tokens to one output token, that is $4.50 per million tokens for Gemini 3.1 Pro Preview versus $6.00 for Kimi K3 (1.3× as much) and $10.00 for Claude Opus 4.6 (2.2× as much).
Which scores higher on benchmarks?
Kimi K3 scores higher on the Capabilities Index (ECI): Kimi K3 157.6 (#13 of 148), Claude Opus 4.6 155.3 (#27 of 148) and Gemini 3.1 Pro Preview 154.8 (#31 of 148). The confidence ranges of the top two overlap (154.9–160.4 vs 153.4–157.3), so treat the gap as small. On individual benchmarks: GPQA Diamond — Gemini 3.1 Pro Preview 94.4%, Kimi K3 93.1%, Claude Opus 4.6 90.5%; FrontierMath Tiers 1–3 — Kimi K3 72.2%, Claude Opus 4.6 66.0%, Gemini 3.1 Pro Preview 59.7%; OTIS Mock AIME 2024–2025 — Kimi K3 97.2%, Gemini 3.1 Pro Preview 95.6%, Claude Opus 4.6 94.4%; SimpleQA Verified — Gemini 3.1 Pro Preview 73.5%, Kimi K3 50.6%, Claude Opus 4.6 47.0%.
Which is better for coding?
There are no published SWE-bench Verified results for Kimi K3 yet, so there is no like-for-like coding score. On overall capability, Kimi K3 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?
Kimi K3 and Gemini 3.1 Pro Preview have the largest context windows (1,048,576 and 1,048,576 tokens), against 1,000,000 for Claude Opus 4.6. Maximum output per response: Claude Opus 4.6 up to 128,000, Kimi K3 up to 131,072, Gemini 3.1 Pro Preview up to 65,536 tokens.
Which can read images, PDFs, audio or video?
Claude Opus 4.6 accepts text, images and PDFs; Kimi K3 accepts text, images and video; Gemini 3.1 Pro Preview accepts text, images, PDFs, audio and video. Gemini 3.1 Pro Preview handles the widest range of inputs.
Are any of these open source?
Kimi K3 publishes its weights and can be self-hosted; Claude Opus 4.6 and Gemini 3.1 Pro Preview is proprietary.
Which is newer?
Kimi K3 is the newest, released Jul 16, 2026. Gemini 3.1 Pro Preview came out Feb 19, 2026; Claude Opus 4.6 came out Feb 5, 2026. Knowledge cutoff: Claude Opus 4.6 May 31, 2025, Gemini 3.1 Pro Preview Jan 2025.
How do you decide the winner?
Each model gets a 0–100 score on 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 Oct 4, 2026.
