Kimi K2 Instruct vs Nex-N2-Pro vs Qwen3 235B-A22B Thinking 2507
No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.
Price in rating: Included · Exclude price
Moonshot AI
Kimi K2 Instruct
38/100- ECI141.3
- Price$0.57 / $2.30
- Context131K
Nex AGI
Nex-N2-Pro
50/100- ECI—
- Price$0.50 / $2.50
- Context262K
Alibaba (Qwen)
Qwen3 235B-A22B Thinking 2507
43/100- ECI143.3
- Price$0.30 / $2.90
- Context262K
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (Nex-N2-Pro 50/100, Qwen3 235B-A22B Thinking 2507 43/100, Kimi K2 Instruct 38/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. 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 priceQwen3 235B-A22B Thinking 2507Qwen3 235B-A22B Thinking 2507 $0.95 · Nex-N2-Pro $1.00 · Kimi K2 Instruct $1.00 per 1M tokens (3:1 blend)
- Longest contextNex-N2-Pro and Qwen3 235B-A22B Thinking 2507Nex-N2-Pro 262,144 · Qwen3 235B-A22B Thinking 2507 262,144 · Kimi K2 Instruct 131,072 tokens
- Widest inputsNex-N2-ProKimi K2 Instruct: Text · Nex-N2-Pro: Text, Images · Qwen3 235B-A22B Thinking 2507: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Kimi K2 Instruct | Nex-N2-Pro | Qwen3 235B-A22B Thinking 2507 |
|---|---|---|---|---|
| Price | 50% | 48 | 48 | 49 |
| Inputs & features | 30% | 25 | 60 | 35 |
| Context window | 20% | 32 | 43 | 43 |
| Specs & price only | 100% | 38/100 | 50/100 | 43/100 |
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 | Nex-N2-ProNex AGI | ||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 141.3 | — | 143.3 (best) |
| ECI rank | #108 of 158 | — | #100 of 158 (best) |
| GPQA DiamondGraduate-level science questions | — | — | 80.1% |
| OTIS Mock AIME 2024–2025Competition mathematics | — | — | 86.7% |
| SimpleQA VerifiedShort factual questions | — | — | 40.4% |
| Price per million tokens | |||
| Input | $0.57 | $0.50 | $0.30 (best) |
| Output | $2.30 (best) | $2.50 | $2.90 |
| Cached input | — | — | — |
| Blended (3:1) | $1.00 | $1.00 | $0.95 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 11 providers | Median of 1 providers | Median of 11 providers |
| Limits | |||
| Context window | 131,072 tokens | 262,144 tokens (best) | 262,144 tokens (best) |
| Max output | 32,768 tokens | 262,144 tokens (best) | 81,920 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | OpenModified MIT | Open | OpenApache 2.0 |
| API model ID | — | — | — |
| API providers | 11 | 1 | 12 (best) |
| Released | Jul 11, 2025 | Jun 2, 2026 | Jul 25, 2025 |
| Knowledge cutoff | — | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Kimi K2 Instruct$10.30
- Nex-N2-Pro$10.00
Qwen3 235B-A22B Thinking 2507$8.80
Which should you choose?
Which is better: Kimi K2 Instruct, Nex-N2-Pro or Qwen3 235B-A22B Thinking 2507?
There is not enough shared capability evidence to name an overall winner. The scores (Nex-N2-Pro 50/100, Qwen3 235B-A22B Thinking 2507 43/100, Kimi K2 Instruct 38/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Kimi K2 Instruct, Nex-N2-Pro or Qwen3 235B-A22B Thinking 2507?
Qwen3 235B-A22B Thinking 2507 is cheaper at $0.30 input / $2.90 output per million tokens (median across 11 API providers). Nex-N2-Pro costs $0.50 input / $2.50 output per million tokens (median across 1 API provider); Kimi K2 Instruct costs $0.57 input / $2.30 output per million tokens (median across 11 API providers). At a typical mix of three input tokens to one output token, that is $0.95 per million tokens for Qwen3 235B-A22B Thinking 2507 versus $1.00 for Nex-N2-Pro (1.1× as much) and $1.00 for Kimi K2 Instruct (1.1× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Kimi K2 Instruct has an ECI of 141.3, Nex-N2-Pro has not been scored yet and Qwen3 235B-A22B Thinking 2507 has an ECI of 143.3.
Which is better for coding?
There are no published SWE-bench Verified results for Kimi K2 Instruct, Nex-N2-Pro and Qwen3 235B-A22B Thinking 2507 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?
Nex-N2-Pro and Qwen3 235B-A22B Thinking 2507 have the largest context windows (262,144 and 262,144 tokens), against 131,072 for Kimi K2 Instruct. Maximum output per response: Kimi K2 Instruct up to 32,768, Nex-N2-Pro up to 262,144, Qwen3 235B-A22B Thinking 2507 up to 81,920 tokens.
Which can read images, PDFs, audio or video?
Kimi K2 Instruct accepts text; Nex-N2-Pro accepts text and images; Qwen3 235B-A22B Thinking 2507 accepts text. Nex-N2-Pro handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (Modified MIT and Apache 2.0), so you can self-host them.
Which is newer?
Nex-N2-Pro is the newest, released Jun 2, 2026. Qwen3 235B-A22B Thinking 2507 came out Jul 25, 2025; Kimi K2 Instruct came out Jul 11, 2025.
How do you decide the winner?
This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, 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.