MinerU2.5 2509 1.2B vs GPT-5-Codex
No independent capability benchmark covers every model here yet. The score uses price and context window.No independent capability benchmark covers every model here yet. The score uses context window.
Opendatalab
MinerU2.5 2509 1.2B
71/100- ECI—
- Price$0.024 / $0.071
- Context16K
OpenAI
GPT-5-Codex
31/100- ECI—
- Price$1.25 / $10.00
- Context400K
Opendatalab
MinerU2.5 2509 1.2B
0/100- ECI—
- Price$0.024 / $0.071
- Context16K
OpenAI
GPT-5-Codex
50/100- ECI—
- Price$1.25 / $10.00
- Context400K
Add a model
Make it a three-way comparison.
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (MinerU2.5 2509 1.2B 71/100, GPT-5-Codex 31/100) compare the available specifications and price. The score weighs price 71%, context window 29%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.There is not enough shared capability evidence to name an overall winner. The scores (GPT-5-Codex 50/100, MinerU2.5 2509 1.2B 0/100) compare the available specifications only. The score weighs context window 100%. 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 priceMinerU2.5 2509 1.2BMinerU2.5 2509 1.2B $0.036 · GPT-5-Codex $3.44 per 1M tokens (3:1 blend)
- Longest contextGPT-5-CodexGPT-5-Codex 400,000 · MinerU2.5 2509 1.2B 16,384 tokens
- Widest inputsSame inputsMinerU2.5 2509 1.2B: Text, Images · GPT-5-Codex: Text, Images
- Self-hostingMinerU2.5 2509 1.2BPublishes downloadable weights (AGPL-3.0)
| Measure | Weight | MinerU2.5 2509 1.2B | GPT-5-Codex |
|---|---|---|---|
| Price | 71% | 100 | 23 |
| Context window | 29% | 0 | 50 |
| Specs & price only | 100% | 71/100 | 31/100 |
Left out because at least one model lacks the data: capability and inputs & features. The remaining weights were rescaled.
| Measure | Weight | MinerU2.5 2509 1.2B | GPT-5-Codex |
|---|---|---|---|
| Context window | 100% | 0 | 50 |
| Specs only | 100% | 0/100 | 50/100 |
Left out because at least one model lacks the data: capability and inputs & features. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Unavailable specifications are marked “Not published”. Publisher results include their evaluation settings and source.
| Specification | ||
|---|---|---|
| Capability | ||
| Capabilities Index (ECI) | Not published | Not published |
| ECI rank | Not published | Not published |
| ECI confidence interval | Not published | Not published |
| ECI evaluation date | Not published | Not published |
| Documented capabilities | 1.2B-parameter vision-language model from OpenDataLab for two-step document parsing: global layout analysis on downsampled images, then fine-grained text, formula, and table recognition at native resolution | Coding-optimized GPT model for repository edits, reviews, and agentic software work |
| Model parameters | Not published | Not published |
| Output modalities | Text | Text |
| Publisher-reported benchmarks | ||
| Artificial Analysis Coding IndexPublisher-reported result | Not published | 38.9indexReported resultJun 1, 2026 |
| SciCodePublisher-reported result | Not published | 40.9percent correctReported resultJun 1, 2026 |
| Terminal-Bench HardPublisher-reported result | Not published | 37.9success rateReported resultJun 1, 2026 |
| Price per million tokens | ||
| Input | $0.024 (best) | $1.25 |
| Output | $0.071 (best) | $10.00 |
| Cached input | Not published | Not published |
| Blended (3:1) | $0.036 (best) | $3.44 |
| Long-context rate | Same rate | Same rate |
| Price source | Median of 1 providers | Median of 9 providers |
| Limits | ||
| Context window | 16,384 tokens | 400,000 tokens (best) |
| Max input | Not published | 272,000 tokens |
| Max output | Not published | 128,000 tokens |
| Inputs and features | ||
| Text | Yes | Yes |
| Images | Yes | Yes |
| PDFs | No | No |
| Audio | No | No |
| Video | No | No |
| Reasoning | No | Yes |
| Tool calling | No | Yes |
| Structured output | Not published | Not published |
| File attachments | Yes | Yes |
| Temperature control | Yes | No |
| Reasoning control | Not published | always |
| Availability | ||
| Weights | OpenAGPL-3.0 | Proprietary |
| API model ID | Not published | Not published |
| API providers | 1 | 10 (best) |
| Released | Sep 17, 2025 | Sep 15, 2025 |
| Knowledge cutoff | Not published | Sep 30, 2024 |
| Publisher documentation | Model weights | Not published |
| Source metadata updated | Sep 17, 2025 | Sep 15, 2025 |
| Data sources | models.dev · Epoch AI | models.dev · Epoch AI |
| Catalog checked | Nov 22, 2026 | Nov 22, 2026 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
MinerU2.5 2509 1.2B$0.381
GPT-5-Codex$32.50
Which should you choose?
Which is better: MinerU2.5 2509 1.2B or GPT-5-Codex?
There is not enough shared capability evidence to name an overall winner. The scores (MinerU2.5 2509 1.2B 71/100, GPT-5-Codex 31/100) compare the available specifications and price. The score weighs price 71%, context window 29%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.There is not enough shared capability evidence to name an overall winner. The scores (GPT-5-Codex 50/100, MinerU2.5 2509 1.2B 0/100) compare the available specifications only. The score weighs context window 100%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, MinerU2.5 2509 1.2B or GPT-5-Codex?
MinerU2.5 2509 1.2B is cheaper at $0.024 input / $0.071 output per million tokens (median across 1 API provider). GPT-5-Codex costs $1.25 input / $10.00 output per million tokens (median across 9 API providers). At a typical mix of three input tokens to one output token, that is $0.036 per million tokens for MinerU2.5 2509 1.2B versus $3.44 for GPT-5-Codex (96× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers both models yet. MinerU2.5 2509 1.2B has not been scored yet and GPT-5-Codex has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for MinerU2.5 2509 1.2B and GPT-5-Codex yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that MinerU2.5 2509 1.2B has no confirmed tool-calling support in this comparison.
Which has the bigger context window?
GPT-5-Codex has the largest context window at 400,000 tokens, against 16,384 for MinerU2.5 2509 1.2B. Maximum output per response: GPT-5-Codex up to 128,000 tokens.
Which can read images, PDFs, audio or video?
MinerU2.5 2509 1.2B accepts text and images; GPT-5-Codex accepts text and images. They handle the same number of input types.
Are any of these open source?
MinerU2.5 2509 1.2B publishes its weights (AGPL-3.0) and can be self-hosted; GPT-5-Codex is proprietary.
Which is newer?
MinerU2.5 2509 1.2B is the newest, released Sep 17, 2025. GPT-5-Codex came out Sep 15, 2025. Knowledge cutoff: GPT-5-Codex Sep 30, 2024.
How do you decide the winner?
This rating uses price (71%, blended price per million tokens (3 input : 1 output), log scale); context window (29%, 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 22, 2026.This rating uses context window (100%, 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 22, 2026.