Gemini 4 Argon vs GPT-5.6 Terra vs Kimi K3.1 Pro
Gemini 4 Argon comes out ahead, 91 to 83 and 83 on our weighted score.
Price in rating: Excluded · Include price
- Our pick
Google
Gemini 4 Argon
91/100- ECI166.6
- Price$2.00 / $10.00
- Context1.05M
OpenAI
GPT-5.6 Terra
83/100- ECI160.8
- Price$2.00 / $12.00
- Context1.05M
Moonshot AI
Kimi K3.1 Pro
83/100- ECI161.4
- Price$2.00 / $10.00
- Context1.05M
Gemini 4 Argon is our pick
Gemini 4 Argon is the better all-round choice, scoring 91/100 against Kimi K3.1 Pro (83) and GPT-5.6 Terra (83). It leads on capability and inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.
- CapabilityGemini 4 ArgonCapabilities Index (ECI): Gemini 4 Argon 166.6 · Kimi K3.1 Pro 161.4 · GPT-5.6 Terra 160.8
- Lowest priceGemini 4 Argon and Kimi K3.1 ProGemini 4 Argon $4.00 · Kimi K3.1 Pro $4.00 · GPT-5.6 Terra $4.50 per 1M tokens (3:1 blend)
- Longest contextAbout the sameGPT-5.6 Terra 1,050,000 · Gemini 4 Argon 1,048,576 · Kimi K3.1 Pro 1,048,576 tokens
- Widest inputsGemini 4 ArgonGemini 4 Argon: Text, Images, PDFs, Audio, Video · GPT-5.6 Terra: Text, Images, PDFs · Kimi K3.1 Pro: Text, Images, Video
- Self-hostingKimi K3.1 ProPublishes downloadable weights
| Measure | Weight | Gemini 4 Argon | GPT-5.6 Terra | Kimi K3.1 Pro |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 67% | 93 | 87 | 88 |
| Inputs & features | 20% | 100 | 80 | 80 |
| Context window | 13% | 65 | 65 | 65 |
| Overall | 100% | 91/100 | 83/100 | 83/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 166.6 (best) | 160.8 | 161.4 |
| ECI rank | #10 of 158 (best) | #18 of 158 | #17 of 158 |
| GPQA DiamondGraduate-level science questions | 96.4% (best) | 93.3% | 94.2% |
| FrontierMath Tiers 1–3Research-level mathematics | 86.0% (best) | 86.0% (best) | 78.3% |
| OTIS Mock AIME 2024–2025Competition mathematics | 100% (best) | 99.7% | 100% (best) |
| SimpleQA VerifiedShort factual questions | 76.0% (best) | 43.2% | 62.2% |
| Price per million tokens | |||
| Input | $2.00 | $2.00 | $2.00 |
| Output | $10.00 (best) | $12.00 | $10.00 (best) |
| Cached input | $0.10 (best) | $0.20 | $0.20 |
| Blended (3:1) | $4.00 (best) | $4.50 | $4.00 (best) |
| Long-context rate | Same rate | Over 272K: $4.00 / $18.00 | Same rate |
| Price source | Official Google API | Official OpenAI API | Official Moonshot AI API |
| Limits | |||
| Context window | 1,048,576 tokens | 1,050,000 tokens (best) | 1,048,576 tokens |
| Max output | 65,536 tokens | 128,000 tokens | 1,048,576 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | Yes | Yes | No |
| Audio | Yes | No | No |
| Video | Yes | No | Yes |
| Reasoning | Yeslow · medium · high | Yeslow · medium · high · xhigh · max | Yeslow · high · max |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | Yes |
| Availability | |||
| Weights | Proprietary | Proprietary | Open |
| API model ID | gemini-4-argon | gpt-5.6-terra | kimi-k3.1-pro |
| API providers | 32 | 56 | 57 (best) |
| Released | Oct 13, 2026 | Jul 9, 2026 | Oct 23, 2026 |
| Knowledge cutoff | Mar 2026 | Feb 16, 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
GPT-5.6 Terra$44.00
Kimi K3.1 Pro$40.00
Which should you choose?
Which is better: Gemini 4 Argon, GPT-5.6 Terra or Kimi K3.1 Pro?
Gemini 4 Argon is the better all-round choice, scoring 91/100 against Kimi K3.1 Pro (83) and GPT-5.6 Terra (83). It leads on capability and inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.
Which is cheaper, Gemini 4 Argon, GPT-5.6 Terra or Kimi K3.1 Pro?
Gemini 4 Argon is cheaper at $2.00 input / $10.00 output per million tokens (official Google API price). Kimi K3.1 Pro costs $2.00 input / $10.00 output per million tokens (official Moonshot AI API price); GPT-5.6 Terra costs $2.00 input / $12.00 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $4.00 per million tokens for Gemini 4 Argon versus $4.00 for Kimi K3.1 Pro (1× as much) and $4.50 for GPT-5.6 Terra (1.1× as much).
Which scores higher on benchmarks?
Gemini 4 Argon scores higher on the Capabilities Index (ECI): Gemini 4 Argon 166.6 (#10 of 158), Kimi K3.1 Pro 161.4 (#17 of 158) and GPT-5.6 Terra 160.8 (#18 of 158). Their confidence ranges do not overlap (163.9–169.5 vs 159.0–163.9), so the gap is a real one. On individual benchmarks: GPQA Diamond — Gemini 4 Argon 96.4%, Kimi K3.1 Pro 94.2%, GPT-5.6 Terra 93.3%; FrontierMath Tiers 1–3 — Gemini 4 Argon 86.0%, GPT-5.6 Terra 86.0%, Kimi K3.1 Pro 78.3%; OTIS Mock AIME 2024–2025 — Gemini 4 Argon 100%, Kimi K3.1 Pro 100%, GPT-5.6 Terra 99.7%; SimpleQA Verified — Gemini 4 Argon 76.0%, Kimi K3.1 Pro 62.2%, GPT-5.6 Terra 43.2%.
Which is better for coding?
There are no published SWE-bench Verified results for Gemini 4 Argon, GPT-5.6 Terra and Kimi K3.1 Pro yet, so there is no like-for-like coding score. On overall capability, Gemini 4 Argon 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?
Their context windows are effectively the same size: Gemini 4 Argon 1,048,576, GPT-5.6 Terra 1,050,000 and Kimi K3.1 Pro 1,048,576 tokens. Maximum output per response: Gemini 4 Argon up to 65,536, GPT-5.6 Terra up to 128,000, Kimi K3.1 Pro up to 1,048,576 tokens.
Which can read images, PDFs, audio or video?
Gemini 4 Argon accepts text, images, PDFs, audio and video; GPT-5.6 Terra accepts text, images and PDFs; Kimi K3.1 Pro accepts text, images and video. 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 GPT-5.6 Terra is proprietary.
Which is newer?
Kimi K3.1 Pro is the newest, released Oct 23, 2026. Gemini 4 Argon came out Oct 13, 2026; GPT-5.6 Terra came out Jul 9, 2026. Knowledge cutoff: Gemini 4 Argon Mar 2026, GPT-5.6 Terra Feb 16, 2026.
How do you decide the winner?
This rating uses capability (67%, independent benchmark results); inputs & features (20%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (13%, 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.