Kimi K2 Instruct vs Qwen3 235B-A22B Thinking 2507 vs WizardLM 2 8x22B
No independent capability benchmark covers every model here yet. The score uses inputs & features and context window.
Price in rating: Excluded · Include price
Moonshot AI
Kimi K2 Instruct
28/100- ECI141.3
- Price$0.57 / $2.30
- Context131K
Alibaba (Qwen)
Qwen3 235B-A22B Thinking 2507
38/100- ECI143.3
- Price$0.30 / $2.90
- Context262K
Microsoft
WizardLM 2 8x22B
9/100- ECI—
- Price$0.493 / $0.493
- Context66K
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (Qwen3 235B-A22B Thinking 2507 38/100, Kimi K2 Instruct 28/100, WizardLM 2 8x22B 9/100) 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 priceWizardLM 2 8x22BWizardLM 2 8x22B $0.493 · Qwen3 235B-A22B Thinking 2507 $0.95 · Kimi K2 Instruct $1.00 per 1M tokens (3:1 blend)
- Longest contextQwen3 235B-A22B Thinking 2507Qwen3 235B-A22B Thinking 2507 262,144 · Kimi K2 Instruct 131,072 · WizardLM 2 8x22B 65,536 tokens
- Widest inputsSame inputsKimi K2 Instruct: Text · Qwen3 235B-A22B Thinking 2507: Text · WizardLM 2 8x22B: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Kimi K2 Instruct | Qwen3 235B-A22B Thinking 2507 | WizardLM 2 8x22B |
|---|---|---|---|---|
| Inputs & features | 60% | 25 | 35 | 0 |
| Context window | 40% | 32 | 43 | 22 |
| Specs only | 100% | 28/100 | 38/100 | 9/100 |
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 | |||
|---|---|---|---|
| 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% (best) | 43.4% |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 86.7% | — |
| SimpleQA VerifiedShort factual questions | — | 40.4% | — |
| Price per million tokens | |||
| Input | $0.57 | $0.30 (best) | $0.493 |
| Output | $2.30 | $2.90 | $0.493 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $1.00 | $0.95 | $0.493 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 11 providers | Median of 11 providers | Median of 3 providers |
| Limits | |||
| Context window | 131,072 tokens | 262,144 tokens (best) | 65,536 tokens |
| Max output | 32,768 tokens | 81,920 tokens (best) | 8,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | Yes | No |
| Tool calling | Yes | Yes | No |
| Structured output | No | No | No |
| Availability | |||
| Weights | OpenModified MIT | OpenApache 2.0 | OpenApache-2.0 |
| API model ID | — | — | — |
| API providers | 11 | 12 (best) | 3 |
| Released | Jul 11, 2025 | Jul 25, 2025 | Apr 15, 2024 |
| 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
Qwen3 235B-A22B Thinking 2507$8.80
WizardLM 2 8x22B$5.92
Which should you choose?
Which is better: Kimi K2 Instruct, Qwen3 235B-A22B Thinking 2507 or WizardLM 2 8x22B?
There is not enough shared capability evidence to name an overall winner. The scores (Qwen3 235B-A22B Thinking 2507 38/100, Kimi K2 Instruct 28/100, WizardLM 2 8x22B 9/100) 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, Kimi K2 Instruct, Qwen3 235B-A22B Thinking 2507 or WizardLM 2 8x22B?
WizardLM 2 8x22B is cheaper at $0.493 input / $0.493 output per million tokens (median across 3 API providers). Qwen3 235B-A22B Thinking 2507 costs $0.30 input / $2.90 output per million tokens (median across 11 API providers); 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 $0.493 per million tokens for WizardLM 2 8x22B versus $0.95 for Qwen3 235B-A22B Thinking 2507 (1.9× as much) and $1.00 for Kimi K2 Instruct (2× 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, Qwen3 235B-A22B Thinking 2507 has an ECI of 143.3 and WizardLM 2 8x22B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Kimi K2 Instruct, Qwen3 235B-A22B Thinking 2507 and WizardLM 2 8x22B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that WizardLM 2 8x22B does not support tool calling, which most coding agents need.
Which has the bigger context window?
Qwen3 235B-A22B Thinking 2507 has the largest context window at 262,144 tokens, against 131,072 for Kimi K2 Instruct and 65,536 for WizardLM 2 8x22B. Maximum output per response: Kimi K2 Instruct up to 32,768, Qwen3 235B-A22B Thinking 2507 up to 81,920, WizardLM 2 8x22B up to 8,000 tokens.
Which can read images, PDFs, audio or video?
Kimi K2 Instruct accepts text; Qwen3 235B-A22B Thinking 2507 accepts text; WizardLM 2 8x22B accepts text. They handle the same number of input types.
Are any of these open source?
Yes, all three publish their weights (Modified MIT, Apache 2.0 and Apache-2.0), so you can self-host them.
Which is newer?
Qwen3 235B-A22B Thinking 2507 is the newest, released Jul 25, 2025. Kimi K2 Instruct came out Jul 11, 2025; WizardLM 2 8x22B came out Apr 15, 2024.
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.