Apertus 1.5 70B vs Grok 4.20 (Reasoning) vs Kimi K2.6
No independent capability benchmark covers every model here yet. The score uses inputs & features and context window.
Price in rating: Excluded · Include price
Swiss AI
Apertus 1.5 70B
59/100- ECI—
- Price$1.16 / $3.94
- Context262K
xAI
Grok 4.20 (Reasoning)
74/100- ECI152.3
- Price$1.25 / $2.50
- Context1M
Moonshot AI
Kimi K2.6
65/100- ECI151.6
- Price$0.95 / $4.00
- Context262K
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (Grok 4.20 (Reasoning) 74/100, Kimi K2.6 65/100, Apertus 1.5 70B 59/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceGrok 4.20 (Reasoning)Grok 4.20 (Reasoning) $1.56 · Kimi K2.6 $1.71 · Apertus 1.5 70B $1.85 per 1M tokens (3:1 blend)
- Longest contextGrok 4.20 (Reasoning)Grok 4.20 (Reasoning) 1,000,000 · Apertus 1.5 70B 262,144 · Kimi K2.6 262,144 tokens
- Widest inputsSame inputsApertus 1.5 70B: Text, Images, Audio · Grok 4.20 (Reasoning): Text, Images, PDFs · Kimi K2.6: Text, Images, Video
- Self-hostingApertus 1.5 70B and Kimi K2.6Publishes downloadable weights (Apache-2.0)
| Measure | Weight | Apertus 1.5 70B | Grok 4.20 (Reasoning) | Kimi K2.6 |
|---|---|---|---|---|
| Inputs & features | 60% | 70 | 80 | 80 |
| Context window | 40% | 43 | 64 | 43 |
| Specs only | 100% | 59/100 | 74/100 | 65/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Apertus 1.5 70BSwiss AI | ||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | 152.3 (best) | 151.6 |
| ECI rank | — | #59 of 158 (best) | #61 of 158 |
| GPQA DiamondGraduate-level science questions | — | 89.3% | 90.8% (best) |
| FrontierMath Tiers 1–3Research-level mathematics | — | 44.9% | 57.2% (best) |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 92.2% | 96.1% (best) |
| SWE-bench VerifiedFixing real GitHub issues | — | — | 76.7% |
| SimpleQA VerifiedShort factual questions | — | 30.2% | 34.9% (best) |
| Price per million tokens | |||
| Input | $1.16 | $1.25 | $0.95 (best) |
| Output | $3.94 | $2.50 (best) | $4.00 |
| Cached input | — | $0.20 | $0.16 (best) |
| Blended (3:1) | $1.85 | $1.56 (best) | $1.71 |
| Long-context rate | Same rate | Over 200K: $2.50 / $5.00 | Same rate |
| Price source | Median of 1 providers | Official xAI API | Official Moonshot AI API |
| Limits | |||
| Context window | 262,144 tokens | 1,000,000 tokens (best) | 262,144 tokens |
| Max output | 8,192 tokens | 30,000 tokens | 262,144 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | Yes | No |
| Audio | Yes | No | No |
| Video | No | No | Yes |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | Yes |
| Availability | |||
| Weights | OpenApache-2.0 | Proprietary | Open |
| API model ID | — | grok-4.20-0309-reasoning | kimi-k2.6 |
| API providers | 1 | 14 | 64 (best) |
| Released | Jul 24, 2026 | Mar 9, 2026 | Apr 20, 2026 |
| Knowledge cutoff | — | — | 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.
- Apertus 1.5 70B$19.48
Grok 4.20 (Reasoning)$17.50
Kimi K2.6$17.50
Which should you choose?
Which is better: Apertus 1.5 70B, Grok 4.20 (Reasoning) or Kimi K2.6?
There is not enough shared capability evidence to name an overall winner. The scores (Grok 4.20 (Reasoning) 74/100, Kimi K2.6 65/100, Apertus 1.5 70B 59/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Apertus 1.5 70B, Grok 4.20 (Reasoning) or Kimi K2.6?
Grok 4.20 (Reasoning) is cheaper at $1.25 input / $2.50 output per million tokens (official xAI API price). Kimi K2.6 costs $0.95 input / $4.00 output per million tokens (official Moonshot AI API price); Apertus 1.5 70B costs $1.16 input / $3.94 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $1.56 per million tokens for Grok 4.20 (Reasoning) versus $1.71 for Kimi K2.6 (1.1× as much) and $1.85 for Apertus 1.5 70B (1.2× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Apertus 1.5 70B has not been scored yet, Grok 4.20 (Reasoning) has an ECI of 152.3 and Kimi K2.6 has an ECI of 151.6.
Which is better for coding?
There are no published SWE-bench Verified results for Apertus 1.5 70B and Grok 4.20 (Reasoning) yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Grok 4.20 (Reasoning) has the largest context window at 1,000,000 tokens, against 262,144 for Apertus 1.5 70B and 262,144 for Kimi K2.6. Maximum output per response: Apertus 1.5 70B up to 8,192, Grok 4.20 (Reasoning) up to 30,000, Kimi K2.6 up to 262,144 tokens.
Which can read images, PDFs, audio or video?
Apertus 1.5 70B accepts text, images and audio; Grok 4.20 (Reasoning) accepts text, images and PDFs; Kimi K2.6 accepts text, images and video. They handle the same number of input types.
Are any of these open source?
Apertus 1.5 70B and Kimi K2.6 publishes its weights (Apache-2.0) and can be self-hosted; Grok 4.20 (Reasoning) is proprietary.
Which is newer?
Apertus 1.5 70B is the newest, released Jul 24, 2026. Kimi K2.6 came out Apr 20, 2026; Grok 4.20 (Reasoning) came out Mar 9, 2026. Knowledge cutoff: Kimi K2.6 Jan 2025.
How do you decide the winner?
This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, 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.