GPT-5.2 vs Kimi K2 Instruct vs Qwen3 235B-A22B Thinking 2507
GPT-5.2 comes out ahead, 60 to 57 and 53 on our weighted score, though Qwen3 235B-A22B Thinking 2507 is 5.1× cheaper per token.
Price in rating: Included · Exclude price
- Our pick
OpenAI
GPT-5.2
60/100- ECI154.5
- Price$1.75 / $14.00
- Context400K
Moonshot AI
Kimi K2 Instruct
53/100- ECI141.3
- Price$0.57 / $2.30
- Context131K
Alibaba (Qwen)
Qwen3 235B-A22B Thinking 2507
57/100- ECI143.3
- Price$0.30 / $2.90
- Context262K
GPT-5.2 is our pick
GPT-5.2 is the better all-round choice, scoring 60/100 against Qwen3 235B-A22B Thinking 2507 (57) and Kimi K2 Instruct (53). It leads on capability, inputs & features and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityGPT-5.2Capabilities Index (ECI): GPT-5.2 154.5 · Qwen3 235B-A22B Thinking 2507 143.3 · Kimi K2 Instruct 141.3
- Lowest priceQwen3 235B-A22B Thinking 2507Qwen3 235B-A22B Thinking 2507 $0.95 · Kimi K2 Instruct $1.00 · GPT-5.2 $4.81 per 1M tokens (3:1 blend)
- Longest contextGPT-5.2GPT-5.2 400,000 · Qwen3 235B-A22B Thinking 2507 262,144 · Kimi K2 Instruct 131,072 tokens
- Widest inputsGPT-5.2GPT-5.2: Text, Images · Kimi K2 Instruct: Text · Qwen3 235B-A22B Thinking 2507: Text
- Self-hostingKimi K2 Instruct and Qwen3 235B-A22B Thinking 2507Publishes downloadable weights (Modified MIT and Apache 2.0)
| Measure | Weight | GPT-5.2 | Kimi K2 Instruct | Qwen3 235B-A22B Thinking 2507 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 82 | 69 | 71 |
| Price | 25% | 17 | 48 | 49 |
| Inputs & features | 15% | 70 | 25 | 35 |
| Context window | 10% | 50 | 32 | 43 |
| Overall | 100% | 60/100 | 53/100 | 57/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 154.5 (best) | 141.3 | 143.3 |
| ECI rank | #51 of 158 (best) | #108 of 158 | #100 of 158 |
| GPQA DiamondGraduate-level science questions | 91.4% (best) | — | 80.1% |
| FrontierMath Tiers 1–3Research-level mathematics | 67.4% | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 96.1% (best) | — | 86.7% |
| SWE-bench VerifiedFixing real GitHub issues | 73.8% | — | — |
| SimpleQA VerifiedShort factual questions | 37.1% | — | 40.4% (best) |
| Price per million tokens | |||
| Input | $1.75 | $0.57 | $0.30 (best) |
| Output | $14.00 | $2.30 (best) | $2.90 |
| Cached input | $0.175 | — | — |
| Blended (3:1) | $4.81 | $1.00 | $0.95 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official OpenAI API | Median of 11 providers | Median of 11 providers |
| Limits | |||
| Context window | 400,000 tokens (best) | 131,072 tokens | 262,144 tokens |
| Max output | 128,000 tokens (best) | 32,768 tokens | 81,920 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yeslow · medium · high · xhigh | No | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Proprietary | OpenModified MIT | OpenApache 2.0 |
| API model ID | gpt-5.2 | — | — |
| API providers | 36 (best) | 11 | 12 |
| Released | Dec 11, 2025 | Jul 11, 2025 | Jul 25, 2025 |
| Knowledge cutoff | Aug 31, 2025 | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
GPT-5.2$45.50
Kimi K2 Instruct$10.30
Qwen3 235B-A22B Thinking 2507$8.80
Which should you choose?
Which is better: GPT-5.2, Kimi K2 Instruct or Qwen3 235B-A22B Thinking 2507?
GPT-5.2 is the better all-round choice, scoring 60/100 against Qwen3 235B-A22B Thinking 2507 (57) and Kimi K2 Instruct (53). It leads on capability, inputs & features and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, GPT-5.2, Kimi K2 Instruct 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). Kimi K2 Instruct costs $0.57 input / $2.30 output per million tokens (median across 11 API providers); GPT-5.2 costs $1.75 input / $14.00 output per million tokens (official OpenAI API price). 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 Kimi K2 Instruct (1.1× as much) and $4.81 for GPT-5.2 (5.1× as much).
Which scores higher on benchmarks?
GPT-5.2 scores higher on the Capabilities Index (ECI): GPT-5.2 154.5 (#51 of 158), Qwen3 235B-A22B Thinking 2507 143.3 (#100 of 158) and Kimi K2 Instruct 141.3 (#108 of 158). Their confidence ranges do not overlap (152.9–156.3 vs 141.4–145.1), so the gap is a real one.
Which is better for coding?
There are no published SWE-bench Verified results for Kimi K2 Instruct and Qwen3 235B-A22B Thinking 2507 yet, so there is no like-for-like coding score. On overall capability, GPT-5.2 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?
GPT-5.2 has the largest context window at 400,000 tokens, against 262,144 for Qwen3 235B-A22B Thinking 2507 and 131,072 for Kimi K2 Instruct. Maximum output per response: GPT-5.2 up to 128,000, Kimi K2 Instruct up to 32,768, Qwen3 235B-A22B Thinking 2507 up to 81,920 tokens.
Which can read images, PDFs, audio or video?
GPT-5.2 accepts text and images; Kimi K2 Instruct accepts text; Qwen3 235B-A22B Thinking 2507 accepts text. GPT-5.2 handles the widest range of inputs.
Are any of these open source?
Kimi K2 Instruct and Qwen3 235B-A22B Thinking 2507 publishes its weights (Modified MIT and Apache 2.0) and can be self-hosted; GPT-5.2 is proprietary.
Which is newer?
GPT-5.2 is the newest, released Dec 11, 2025. Qwen3 235B-A22B Thinking 2507 came out Jul 25, 2025; Kimi K2 Instruct came out Jul 11, 2025. Knowledge cutoff: GPT-5.2 Aug 31, 2025.
How do you decide the winner?
This rating uses capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, 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.