GPT-3.5-turbo vs GPT-4 vs Qwen Plus Character (Japanese)
Qwen Plus Character (Japanese) comes out ahead, 36 to 28 and 8 on our weighted score, and it is the cheaper option too.
OpenAIGPT-3.5-turbo
28/100- ECI—
- Price$0.50 / $1.50
- Context16K
- OpenAI
GPT-4
8/100- ECI—
- Price$30.00 / $60.00
- Context8K
- Our pick
Alibaba (Qwen)Qwen Plus Character (Japanese)
36/100- ECI—
- Price$0.50 / $1.40
- Context8K
Qwen Plus Character (Japanese) is our pick
Qwen Plus Character (Japanese) is the better all-round choice, scoring 36/100 against GPT-3.5-turbo (28) and GPT-4 (8). 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 priceQwen Plus Character (Japanese)Qwen Plus Character (Japanese) $0.725 · GPT-3.5-turbo $0.75 · GPT-4 $37.50 per 1M tokens (3:1 blend)
- Longest contextGPT-3.5-turboGPT-3.5-turbo 16,385 · GPT-4 8,192 · Qwen Plus Character (Japanese) 8,192 tokens
- Widest inputsSame inputsGPT-3.5-turbo: Text · GPT-4: Text · Qwen Plus Character (Japanese): Text
- Self-hostingNo open weightsAll three are available only through APIs
| Measure | Weight | GPT-3.5-turbo | GPT-4 | Qwen Plus Character (Japanese) |
|---|---|---|---|---|
| Price | 50% | 56 | 0 | 57 |
| Inputs & features | 30% | 0 | 25 | 25 |
| Context window | 20% | 0 | 0 | 0 |
| Overall | 100% | 28/100 | 8/100 | 36/100 |
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 | GPT-3.5-turboOpenAI | GPT-4OpenAI | Qwen Plus Character (Japanese)Alibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.50 (best) | $30.00 | $0.50 (best) |
| Output | $1.50 | $60.00 | $1.40 (best) |
| Cached input | Free | — | — |
| Blended (3:1) | $0.75 | $37.50 | $0.725 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official OpenAI API | Official OpenAI API | Official Alibaba API |
| Limits | |||
| Context window | 16,385 tokens (best) | 8,192 tokens | 8,192 tokens |
| Max output | 4,096 tokens | 8,192 tokens (best) | 512 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 | No | No |
| Tool calling | No | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Proprietary | Proprietary | Proprietary |
| API model ID | gpt-3.5-turbo | gpt-4 | qwen-plus-character-ja |
| API providers | 11 (best) | 8 | 1 |
| Released | Mar 1, 2023 | Nov 6, 2023 | Jan 2024 |
| Knowledge cutoff | Sep 1, 2021 | Nov 2023 | Apr 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-3.5-turbo$8.00
- GPT-4$420.00
- Qwen Plus Character (Japanese)$7.80
Which should you choose?
Which is better: GPT-3.5-turbo, GPT-4 or Qwen Plus Character (Japanese)?
Qwen Plus Character (Japanese) is the better all-round choice, scoring 36/100 against GPT-3.5-turbo (28) and GPT-4 (8). 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, GPT-3.5-turbo, GPT-4 or Qwen Plus Character (Japanese)?
Qwen Plus Character (Japanese) is cheaper at $0.50 input / $1.40 output per million tokens (official Alibaba API price). GPT-3.5-turbo costs $0.50 input / $1.50 output per million tokens (official OpenAI API price); GPT-4 costs $30.00 input / $60.00 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $0.725 per million tokens for Qwen Plus Character (Japanese) versus $0.75 for GPT-3.5-turbo (1× as much) and $37.50 for GPT-4 (52× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. GPT-3.5-turbo has not been scored yet, GPT-4 has not been scored yet and Qwen Plus Character (Japanese) has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for GPT-3.5-turbo, GPT-4 and Qwen Plus Character (Japanese) yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that GPT-3.5-turbo does not support tool calling, which most coding agents need.
Which has the bigger context window?
GPT-3.5-turbo has the largest context window at 16,385 tokens, against 8,192 for GPT-4 and 8,192 for Qwen Plus Character (Japanese). Maximum output per response: GPT-3.5-turbo up to 4,096, GPT-4 up to 8,192, Qwen Plus Character (Japanese) up to 512 tokens.
Which can read images, PDFs, audio or video?
GPT-3.5-turbo accepts text; GPT-4 accepts text; Qwen Plus Character (Japanese) accepts text. They handle the same number of input types.
Are any of these open source?
No. GPT-3.5-turbo, GPT-4 and Qwen Plus Character (Japanese) are proprietary and only available through APIs and apps.
Which is newer?
Qwen Plus Character (Japanese) is the newest, released Jan 2024. GPT-4 came out Nov 6, 2023; GPT-3.5-turbo came out Mar 1, 2023. Knowledge cutoff: GPT-3.5-turbo Sep 1, 2021, GPT-4 Nov 2023, Qwen Plus Character (Japanese) Apr 2024.
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.
