Gemini 4 Argon vs Kimi K3.1 Pro vs Claude Sonnet 5.5
Gemini 4 Argon comes out ahead, 73 to 70 and 68 on our weighted score.
Price in rating: Included · Exclude price
- Our pick
Google
Gemini 4 Argon
73/100- ECI166.6
- Price$2.00 / $10.00
- Context1.05M
Moonshot AI
Kimi K3.1 Pro
68/100- ECI161.4
- Price$2.00 / $10.00
- Context1.05M
Anthropic
Claude Sonnet 5.5
70/100- ECI166.6
- Price$2.00 / $10.00
- Context1M
Gemini 4 Argon is our pick
Gemini 4 Argon is the better all-round choice, scoring 73/100 against Claude Sonnet 5.5 (70) and Kimi K3.1 Pro (68). It leads on inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityClaude Sonnet 5.5Capabilities Index (ECI): Claude Sonnet 5.5 166.6 · Gemini 4 Argon 166.6 · Kimi K3.1 Pro 161.4
- Lowest priceSame priceGemini 4 Argon $4.00 · Kimi K3.1 Pro $4.00 · Claude Sonnet 5.5 $4.00 per 1M tokens (3:1 blend)
- Longest contextGemini 4 Argon and Kimi K3.1 ProGemini 4 Argon 1,048,576 · Kimi K3.1 Pro 1,048,576 · Claude Sonnet 5.5 1,000,000 tokens
- Widest inputsGemini 4 ArgonGemini 4 Argon: Text, Images, PDFs, Audio, Video · Kimi K3.1 Pro: Text, Images, Video · Claude Sonnet 5.5: Text, Images, PDFs
- Self-hostingKimi K3.1 ProPublishes downloadable weights
| Measure | Weight | Gemini 4 Argon | Kimi K3.1 Pro | Claude Sonnet 5.5 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 93 | 88 | 93 |
| Price | 25% | 20 | 20 | 20 |
| Inputs & features | 15% | 100 | 80 | 80 |
| Context window | 10% | 65 | 65 | 64 |
| Overall | 100% | 73/100 | 68/100 | 70/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 166.6 | 161.4 | 166.6 (best) |
| ECI rank | #10 of 158 | #17 of 158 | #9 of 158 (best) |
| GPQA DiamondGraduate-level science questions | 96.4% (best) | 94.2% | 95.6% |
| FrontierMath Tiers 1–3Research-level mathematics | 86.0% | 78.3% | 88.8% (best) |
| OTIS Mock AIME 2024–2025Competition mathematics | 100% | 100% | 100% |
| SimpleQA VerifiedShort factual questions | 76.0% (best) | 62.2% | 46.5% |
| Price per million tokens | |||
| Input | $2.00 | $2.00 | $2.00 |
| Output | $10.00 | $10.00 | $10.00 |
| Cached input | $0.10 (best) | $0.20 | $0.10 (best) |
| Blended (3:1) | $4.00 | $4.00 | $4.00 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Google API | Official Moonshot AI API | Official Anthropic API |
| Limits | |||
| Context window | 1,048,576 tokens (best) | 1,048,576 tokens (best) | 1,000,000 tokens |
| Max output | 65,536 tokens | 1,048,576 tokens (best) | 128,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | Yes | No | Yes |
| Audio | Yes | No | No |
| Video | Yes | Yes | No |
| Reasoning | Yeslow · medium · high | Yeslow · high · max | Yeslow · medium · high · xhigh · max |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | Yes |
| Availability | |||
| Weights | Proprietary | Open | Proprietary |
| API model ID | gemini-4-argon | kimi-k3.1-pro | claude-sonnet-5-5 |
| API providers | 32 | 57 (best) | 57 (best) |
| Released | Oct 13, 2026 | Oct 23, 2026 | Sep 28, 2026 |
| Knowledge cutoff | Mar 2026 | — | Jun 2026 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Gemini 4 Argon$40.00
Kimi K3.1 Pro$40.00
Claude Sonnet 5.5$40.00
Which should you choose?
Which is better: Gemini 4 Argon, Kimi K3.1 Pro or Claude Sonnet 5.5?
Gemini 4 Argon is the better all-round choice, scoring 73/100 against Claude Sonnet 5.5 (70) and Kimi K3.1 Pro (68). It leads on inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, Gemini 4 Argon, Kimi K3.1 Pro or Claude Sonnet 5.5?
Gemini 4 Argon, Kimi K3.1 Pro and Claude Sonnet 5.5 cost the same: $2.00 input / $10.00 output per million tokens.
Which scores higher on benchmarks?
Claude Sonnet 5.5 scores higher on the Capabilities Index (ECI): Claude Sonnet 5.5 166.6 (#9 of 158), Gemini 4 Argon 166.6 (#10 of 158) and Kimi K3.1 Pro 161.4 (#17 of 158). The confidence ranges of the top two overlap (163.8–169.7 vs 163.9–169.5), so treat the gap as small. On individual benchmarks: GPQA Diamond — Gemini 4 Argon 96.4%, Claude Sonnet 5.5 95.6%, Kimi K3.1 Pro 94.2%; FrontierMath Tiers 1–3 — Claude Sonnet 5.5 88.8%, Gemini 4 Argon 86.0%, Kimi K3.1 Pro 78.3%; OTIS Mock AIME 2024–2025 — Gemini 4 Argon 100%, Kimi K3.1 Pro 100%, Claude Sonnet 5.5 100%; SimpleQA Verified — Gemini 4 Argon 76.0%, Kimi K3.1 Pro 62.2%, Claude Sonnet 5.5 46.5%.
Which is better for coding?
There are no published SWE-bench Verified results for Gemini 4 Argon, Kimi K3.1 Pro and Claude Sonnet 5.5 yet, so there is no like-for-like coding score. On overall capability, Claude Sonnet 5.5 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 4 Argon and Kimi K3.1 Pro have the largest context windows (1,048,576 and 1,048,576 tokens), against 1,000,000 for Claude Sonnet 5.5. Maximum output per response: Gemini 4 Argon up to 65,536, Kimi K3.1 Pro up to 1,048,576, Claude Sonnet 5.5 up to 128,000 tokens.
Which can read images, PDFs, audio or video?
Gemini 4 Argon accepts text, images, PDFs, audio and video; Kimi K3.1 Pro accepts text, images and video; Claude Sonnet 5.5 accepts text, images and PDFs. Gemini 4 Argon handles the widest range of inputs.
Are any of these open source?
Kimi K3.1 Pro publishes its weights and can be self-hosted; Gemini 4 Argon and Claude Sonnet 5.5 is proprietary.
Which is newer?
Kimi K3.1 Pro is the newest, released Oct 23, 2026. Gemini 4 Argon came out Oct 13, 2026; Claude Sonnet 5.5 came out Sep 28, 2026. Knowledge cutoff: Gemini 4 Argon Mar 2026, Claude Sonnet 5.5 Jun 2026.
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.