GPT-5 Mini vs DeepSeek V3 0324 vs Kimi K2 Thinking
GPT-5 Mini comes out ahead, 66 to 58 and 55 on our weighted score, though DeepSeek V3 0324 is 29% cheaper per token.
Price in rating: Included · Exclude price
- Our pick
OpenAI
GPT-5 Mini
66/100- ECI146.0
- Price$0.25 / $2.00
- Context400K
DeepSeek
DeepSeek V3 0324
55/100- ECI135.3
- Price$0.275 / $1.12
- Context164K
Moonshot AI
Kimi K2 Thinking
58/100- ECI145.5
- Price$0.60 / $2.50
- Context262K
GPT-5 Mini is our pick
GPT-5 Mini is the better all-round choice, scoring 66/100 against Kimi K2 Thinking (58) and DeepSeek V3 0324 (55). It leads on inputs & features and context window. DeepSeek V3 0324 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityGPT-5 MiniCapabilities Index (ECI): GPT-5 Mini 146.0 · Kimi K2 Thinking 145.5 · DeepSeek V3 0324 135.3
- Lowest priceDeepSeek V3 0324DeepSeek V3 0324 $0.486 · GPT-5 Mini $0.688 · Kimi K2 Thinking $1.07 per 1M tokens (3:1 blend)
- Longest contextGPT-5 MiniGPT-5 Mini 400,000 · Kimi K2 Thinking 262,144 · DeepSeek V3 0324 163,840 tokens
- Widest inputsGPT-5 MiniGPT-5 Mini: Text, Images · DeepSeek V3 0324: Text · Kimi K2 Thinking: Text
- Self-hostingDeepSeek V3 0324 and Kimi K2 ThinkingPublishes downloadable weights
| Measure | Weight | GPT-5 Mini | DeepSeek V3 0324 | Kimi K2 Thinking |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 74 | 63 | 73 |
| Price | 25% | 55 | 62 | 46 |
| Inputs & features | 15% | 70 | 25 | 35 |
| Context window | 10% | 50 | 36 | 43 |
| Overall | 100% | 66/100 | 55/100 | 58/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 146.0 (best) | 135.3 | 145.5 |
| ECI rank | #88 of 158 (best) | #125 of 158 | #90 of 158 |
| GPQA DiamondGraduate-level science questions | 75.0% | 67.6% | 84.2% (best) |
| FrontierMath Tiers 1–3Research-level mathematics | 46.7% | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 86.7% (best) | 37.8% | 83.1% |
| SWE-bench VerifiedFixing real GitHub issues | 64.7% | — | — |
| SimpleQA VerifiedShort factual questions | 21.6% | — | — |
| Price per million tokens | |||
| Input | $0.25 (best) | $0.275 | $0.60 |
| Output | $2.00 | $1.12 (best) | $2.50 |
| Cached input | $0.025 | — | — |
| Blended (3:1) | $0.688 | $0.486 (best) | $1.07 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official OpenAI API | Median of 13 providers | Median of 14 providers |
| Limits | |||
| Context window | 400,000 tokens (best) | 163,840 tokens | 262,144 tokens |
| Max output | 128,000 tokens | 163,840 tokens | 262,144 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yesminimal · low · medium · high | No | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Proprietary | Open | Open |
| API model ID | gpt-5-mini | — | — |
| API providers | 36 (best) | 13 | 15 |
| Released | Aug 7, 2025 | Mar 24, 2025 | Nov 6, 2025 |
| Knowledge cutoff | May 30, 2024 | — | Aug 2024 |
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 Mini$6.50
DeepSeek V3 0324$4.99
Kimi K2 Thinking$11.00
Which should you choose?
Which is better: GPT-5 Mini, DeepSeek V3 0324 or Kimi K2 Thinking?
GPT-5 Mini is the better all-round choice, scoring 66/100 against Kimi K2 Thinking (58) and DeepSeek V3 0324 (55). It leads on inputs & features and context window. DeepSeek V3 0324 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, GPT-5 Mini, DeepSeek V3 0324 or Kimi K2 Thinking?
DeepSeek V3 0324 is cheaper at $0.275 input / $1.12 output per million tokens (median across 13 API providers). GPT-5 Mini costs $0.25 input / $2.00 output per million tokens (official OpenAI API price); Kimi K2 Thinking costs $0.60 input / $2.50 output per million tokens (median across 14 API providers). At a typical mix of three input tokens to one output token, that is $0.486 per million tokens for DeepSeek V3 0324 versus $0.688 for GPT-5 Mini (1.4× as much) and $1.07 for Kimi K2 Thinking (2.2× as much).
Which scores higher on benchmarks?
GPT-5 Mini scores higher on the Capabilities Index (ECI): GPT-5 Mini 146.0 (#88 of 158), Kimi K2 Thinking 145.5 (#90 of 158) and DeepSeek V3 0324 135.3 (#125 of 158). The confidence ranges of the top two overlap (144.4–147.6 vs 143.7–147.3), so treat the gap as small. On individual benchmarks: GPQA Diamond — Kimi K2 Thinking 84.2%, GPT-5 Mini 75.0%, DeepSeek V3 0324 67.6%; OTIS Mock AIME 2024–2025 — GPT-5 Mini 86.7%, Kimi K2 Thinking 83.1%, DeepSeek V3 0324 37.8%.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek V3 0324 and Kimi K2 Thinking yet, so there is no like-for-like coding score. On overall capability, GPT-5 Mini 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 Mini has the largest context window at 400,000 tokens, against 262,144 for Kimi K2 Thinking and 163,840 for DeepSeek V3 0324. Maximum output per response: GPT-5 Mini up to 128,000, DeepSeek V3 0324 up to 163,840, Kimi K2 Thinking up to 262,144 tokens.
Which can read images, PDFs, audio or video?
GPT-5 Mini accepts text and images; DeepSeek V3 0324 accepts text; Kimi K2 Thinking accepts text. GPT-5 Mini handles the widest range of inputs.
Are any of these open source?
DeepSeek V3 0324 and Kimi K2 Thinking publishes its weights and can be self-hosted; GPT-5 Mini is proprietary.
Which is newer?
Kimi K2 Thinking is the newest, released Nov 6, 2025. GPT-5 Mini came out Aug 7, 2025; DeepSeek V3 0324 came out Mar 24, 2025. Knowledge cutoff: GPT-5 Mini May 30, 2024, Kimi K2 Thinking Aug 2024.
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.