Kimi K2 Thinking vs GPT-4.1 mini vs Qwen3.5 Plus
Qwen3.5 Plus comes out ahead, 66 to 60 and 58 on our weighted score, though GPT-4.1 mini is 22% cheaper per token.
Moonshot AI
Kimi K2 Thinking
58/100- ECI146.0
- Price$0.60 / $2.50
- Context262K
OpenAI
GPT-4.1 mini
60/100- ECI135.0
- Price$0.40 / $1.60
- Context1.05M
- Our pick
Alibaba (Qwen)
Qwen3.5 Plus
66/100- ECI146.8
- Price$0.40 / $2.40
- Context1M
Qwen3.5 Plus is our pick
Qwen3.5 Plus is the better all-round choice, scoring 66/100 against GPT-4.1 mini (60) and Kimi K2 Thinking (58). GPT-4.1 mini wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityQwen3.5 PlusCapabilities Index (ECI): Qwen3.5 Plus 146.8 · Kimi K2 Thinking 146.0 · GPT-4.1 mini 135.0
- Lowest priceGPT-4.1 miniGPT-4.1 mini $0.70 · Qwen3.5 Plus $0.90 · Kimi K2 Thinking $1.07 per 1M tokens (3:1 blend)
- Longest contextGPT-4.1 miniGPT-4.1 mini 1,047,576 · Qwen3.5 Plus 1,000,000 · Kimi K2 Thinking 262,144 tokens
- Widest inputsGPT-4.1 mini and Qwen3.5 PlusKimi K2 Thinking: Text · GPT-4.1 mini: Text, Images, PDFs · Qwen3.5 Plus: Text, Images, Video
- Self-hostingKimi K2 ThinkingPublishes downloadable weights
| Measure | Weight | Kimi K2 Thinking | GPT-4.1 mini | Qwen3.5 Plus |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 73 | 59 | 74 |
| Price | 25% | 48 | 57 | 52 |
| Inputs & features | 15% | 35 | 70 | 70 |
| Context window | 10% | 37 | 61 | 60 |
| Overall | 100% | 58/100 | 60/100 | 66/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 146.0 | 135.0 | 146.8 (best) |
| ECI rank | #72 of 148 | #115 of 148 | #65 of 148 (best) |
| GPQA DiamondGraduate-level science questions | 84.2% | 65.9% | 84.9% (best) |
| FrontierMath Tiers 1–3Research-level mathematics | — | 6.7% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 83.1% | 44.7% | 86.7% (best) |
| SimpleQA VerifiedShort factual questions | — | 12.7% | 25.4% (best) |
| Price per million tokens | |||
| Input | $0.60 | $0.40 (best) | $0.40 (best) |
| Output | $2.50 | $1.60 (best) | $2.40 |
| Cached input | — | $0.10 | — |
| Blended (3:1) | $1.07 | $0.70 (best) | $0.90 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 10 providers | Official OpenAI API | Official Alibaba API |
| Limits | |||
| Context window | 262,144 tokens | 1,047,576 tokens (best) | 1,000,000 tokens |
| Max output | 262,144 tokens (best) | 32,768 tokens | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | Yes | No |
| Audio | No | No | No |
| Video | No | No | Yes |
| Reasoning | Yes | No | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | Open | Proprietary | Proprietary |
| API model ID | — | gpt-4.1-mini | qwen3.5-plus |
| API providers | 10 | 24 (best) | 10 |
| Released | Nov 6, 2025 | Apr 14, 2025 | Feb 16, 2026 |
| Knowledge cutoff | Aug 2024 | Apr 2024 | Apr 2025 |
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 Thinking$11.00
GPT-4.1 mini$7.20
Qwen3.5 Plus$8.80
Which should you choose?
Which is better: Kimi K2 Thinking, GPT-4.1 mini or Qwen3.5 Plus?
Qwen3.5 Plus is the better all-round choice, scoring 66/100 against GPT-4.1 mini (60) and Kimi K2 Thinking (58). GPT-4.1 mini wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, Kimi K2 Thinking, GPT-4.1 mini or Qwen3.5 Plus?
GPT-4.1 mini is cheaper at $0.40 input / $1.60 output per million tokens (official OpenAI API price). Qwen3.5 Plus costs $0.40 input / $2.40 output per million tokens (official Alibaba API price); Kimi K2 Thinking costs $0.60 input / $2.50 output per million tokens (median across 10 API providers). At a typical mix of three input tokens to one output token, that is $0.70 per million tokens for GPT-4.1 mini versus $0.90 for Qwen3.5 Plus (1.3× as much) and $1.07 for Kimi K2 Thinking (1.5× as much).
Which scores higher on benchmarks?
Qwen3.5 Plus scores higher on the Capabilities Index (ECI): Qwen3.5 Plus 146.8 (#65 of 148), Kimi K2 Thinking 146.0 (#72 of 148) and GPT-4.1 mini 135.0 (#115 of 148). The confidence ranges of the top two overlap (144.6–148.1 vs 143.4–147.6), so treat the gap as small. On individual benchmarks: GPQA Diamond — Qwen3.5 Plus 84.9%, Kimi K2 Thinking 84.2%, GPT-4.1 mini 65.9%; OTIS Mock AIME 2024–2025 — Qwen3.5 Plus 86.7%, Kimi K2 Thinking 83.1%, GPT-4.1 mini 44.7%.
Which is better for coding?
There are no published SWE-bench Verified results for Kimi K2 Thinking, GPT-4.1 mini and Qwen3.5 Plus yet, so there is no like-for-like coding score. On overall capability, Qwen3.5 Plus 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-4.1 mini has the largest context window at 1,047,576 tokens, against 1,000,000 for Qwen3.5 Plus and 262,144 for Kimi K2 Thinking. Maximum output per response: Kimi K2 Thinking up to 262,144, GPT-4.1 mini up to 32,768, Qwen3.5 Plus up to 65,536 tokens.
Which can read images, PDFs, audio or video?
Kimi K2 Thinking accepts text; GPT-4.1 mini accepts text, images and PDFs; Qwen3.5 Plus accepts text, images and video. GPT-4.1 mini handles the widest range of inputs.
Are any of these open source?
Kimi K2 Thinking publishes its weights and can be self-hosted; GPT-4.1 mini and Qwen3.5 Plus is proprietary.
Which is newer?
Qwen3.5 Plus is the newest, released Feb 16, 2026. Kimi K2 Thinking came out Nov 6, 2025; GPT-4.1 mini came out Apr 14, 2025. Knowledge cutoff: Kimi K2 Thinking Aug 2024, GPT-4.1 mini Apr 2024, Qwen3.5 Plus Apr 2025.
How do you decide the winner?
Each model gets a 0–100 score on 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 Oct 4, 2026.