Gemini 4 Argon vs GPT-6.1 Terra vs Kimi K3.1 Pro
Gemini 4 Argon comes out ahead, 91 to 87 and 83 on our weighted score, though GPT-6.1 Terra is 2× cheaper per token.
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-6.1 Terra
87/100- ECI167.7
- Price$1.00 / $5.00
- 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 GPT-6.1 Terra (87) and Kimi K3.1 Pro (83). It leads on inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.
- CapabilityGPT-6.1 TerraCapabilities Index (ECI): GPT-6.1 Terra 167.7 · Gemini 4 Argon 166.6 · Kimi K3.1 Pro 161.4
- Lowest priceGPT-6.1 TerraGPT-6.1 Terra $2.00 · Gemini 4 Argon $4.00 · Kimi K3.1 Pro $4.00 per 1M tokens (3:1 blend)
- Longest contextAbout the sameGPT-6.1 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-6.1 Terra: Text, Images, PDFs · Kimi K3.1 Pro: Text, Images, Video
- Self-hostingKimi K3.1 ProPublishes downloadable weights
| Measure | Weight | Gemini 4 Argon | GPT-6.1 Terra | Kimi K3.1 Pro |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 67% | 93 | 94 | 88 |
| Inputs & features | 20% | 100 | 80 | 80 |
| Context window | 13% | 65 | 65 | 65 |
| Overall | 100% | 91/100 | 87/100 | 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 | 167.7 (best) | 161.4 |
| ECI rank | #10 of 158 | #7 of 158 (best) | #17 of 158 |
| GPQA DiamondGraduate-level science questions | 96.4% (best) | 94.3% | 94.2% |
| FrontierMath Tiers 1–3Research-level mathematics | 86.0% | 90.9% (best) | 78.3% |
| OTIS Mock AIME 2024–2025Competition mathematics | 100% | 100% | 100% |
| SimpleQA VerifiedShort factual questions | 76.0% (best) | 57.3% | 62.2% |
| Price per million tokens | |||
| Input | $2.00 | $1.00 (best) | $2.00 |
| Output | $10.00 | $5.00 (best) | $10.00 |
| Cached input | $0.10 | $0.05 (best) | $0.20 |
| Blended (3:1) | $4.00 | $2.00 (best) | $4.00 |
| Long-context rate | Same rate | Over 272K: $2.00 / $7.50 | 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-6.1-terra | kimi-k3.1-pro |
| API providers | 32 | 29 | 57 (best) |
| Released | Oct 13, 2026 | Oct 26, 2026 | Oct 23, 2026 |
| Knowledge cutoff | Mar 2026 | Jun 1, 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-6.1 Terra$20.00
Kimi K3.1 Pro$40.00
Which should you choose?
Which is better: Gemini 4 Argon, GPT-6.1 Terra or Kimi K3.1 Pro?
Gemini 4 Argon is the better all-round choice, scoring 91/100 against GPT-6.1 Terra (87) and Kimi K3.1 Pro (83). It leads on inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.
Which is cheaper, Gemini 4 Argon, GPT-6.1 Terra or Kimi K3.1 Pro?
GPT-6.1 Terra is cheaper at $1.00 input / $5.00 output per million tokens (official OpenAI API price). Gemini 4 Argon costs $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). At a typical mix of three input tokens to one output token, that is $2.00 per million tokens for GPT-6.1 Terra versus $4.00 for Gemini 4 Argon (2× as much) and $4.00 for Kimi K3.1 Pro (2× as much).
Which scores higher on benchmarks?
GPT-6.1 Terra scores higher on the Capabilities Index (ECI): GPT-6.1 Terra 167.7 (#7 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 (164.8–170.9 vs 163.9–169.5), so treat the gap as small. On individual benchmarks: GPQA Diamond — Gemini 4 Argon 96.4%, GPT-6.1 Terra 94.3%, Kimi K3.1 Pro 94.2%; FrontierMath Tiers 1–3 — GPT-6.1 Terra 90.9%, Gemini 4 Argon 86.0%, Kimi K3.1 Pro 78.3%; OTIS Mock AIME 2024–2025 — Gemini 4 Argon 100%, GPT-6.1 Terra 100%, Kimi K3.1 Pro 100%; SimpleQA Verified — Gemini 4 Argon 76.0%, Kimi K3.1 Pro 62.2%, GPT-6.1 Terra 57.3%.
Which is better for coding?
There are no published SWE-bench Verified results for Gemini 4 Argon, GPT-6.1 Terra and Kimi K3.1 Pro yet, so there is no like-for-like coding score. On overall capability, GPT-6.1 Terra 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-6.1 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-6.1 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-6.1 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-6.1 Terra is proprietary.
Which is newer?
GPT-6.1 Terra is the newest, released Oct 26, 2026. Kimi K3.1 Pro came out Oct 23, 2026; Gemini 4 Argon came out Oct 13, 2026. Knowledge cutoff: Gemini 4 Argon Mar 2026, GPT-6.1 Terra Jun 1, 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.