ERNIE 4.5 300B A47B vs Qwen2.5-VL 7B Instruct vs Codestral 25.08
No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.
Price in rating: Included · Exclude price
Retired Qwen2.5-VL 7B Instruct is no longer offered by any provider we track. Its figures are the last published listing, kept so this comparison stays available.
Baidu
ERNIE 4.5 300B A47B
45/100- ECI—
- Price$0.28 / $1.10
- Context131K
Alibaba (Qwen)
Qwen2.5-VL 7B Instruct
51/100- ECI—
- Price$0.35 / $1.05
- Context131K
Mistral AI
Codestral 25.08
49/100- ECI—
- Price$0.30 / $0.90
- Context128K
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (Qwen2.5-VL 7B Instruct 51/100, Codestral 25.08 49/100, ERNIE 4.5 300B A47B 45/100) compare the available specifications and price. 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 priceCodestral 25.08Codestral 25.08 $0.45 · ERNIE 4.5 300B A47B $0.485 · Qwen2.5-VL 7B Instruct $0.525 per 1M tokens (3:1 blend)
- Longest contextERNIE 4.5 300B A47B and Qwen2.5-VL 7B InstructERNIE 4.5 300B A47B 131,072 · Qwen2.5-VL 7B Instruct 131,072 · Codestral 25.08 128,000 tokens
- Widest inputsQwen2.5-VL 7B InstructERNIE 4.5 300B A47B: Text · Qwen2.5-VL 7B Instruct: Text, Images · Codestral 25.08: Text
- Self-hostingERNIE 4.5 300B A47B and Qwen2.5-VL 7B InstructPublishes downloadable weights (Apache-2.0)
| Measure | Weight | ERNIE 4.5 300B A47B | Qwen2.5-VL 7B Instruct | Codestral 25.08 |
|---|---|---|---|---|
| Price | 50% | 62 | 63 | 63 |
| Inputs & features | 30% | 25 | 50 | 35 |
| Context window | 20% | 32 | 24 | 32 |
| Specs & price only | 100% | 45/100 | 51/100 | 49/100 |
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 | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.28 (best) | $0.35 | $0.30 |
| Output | $1.10 | $1.05 | $0.90 (best) |
| Cached input | — | — | $0.03 |
| Blended (3:1) | $0.485 | $0.525 | $0.45 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Official Alibaba API | Official Mistral API |
| Limits | |||
| Context window | 131,072 tokens (best) | 131,072 tokens (best) | 128,000 tokens |
| Max output | 12,000 tokens (best) | 8,192 tokens | 8,192 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | Yes |
| Availability | |||
| Weights | OpenApache-2.0 | Open | Proprietary |
| API model ID | — | qwen2-5-vl-7b-instruct | codestral-2508 |
| API providers | 1 | 1 | 11 (best) |
| Released | Jun 30, 2025 | Sep 2024 | Jul 30, 2025 |
| Knowledge cutoff | — | 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.
ERNIE 4.5 300B A47B$5.00
Qwen2.5-VL 7B Instruct$5.60
Codestral 25.08$4.80
Which should you choose?
Which is better: ERNIE 4.5 300B A47B, Qwen2.5-VL 7B Instruct or Codestral 25.08?
There is not enough shared capability evidence to name an overall winner. The scores (Qwen2.5-VL 7B Instruct 51/100, Codestral 25.08 49/100, ERNIE 4.5 300B A47B 45/100) compare the available specifications and price. 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, ERNIE 4.5 300B A47B, Qwen2.5-VL 7B Instruct or Codestral 25.08?
Codestral 25.08 is cheaper at $0.30 input / $0.90 output per million tokens (official Mistral API price). ERNIE 4.5 300B A47B costs $0.28 input / $1.10 output per million tokens (median across 1 API provider); Qwen2.5-VL 7B Instruct costs $0.35 input / $1.05 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $0.45 per million tokens for Codestral 25.08 versus $0.485 for ERNIE 4.5 300B A47B (1.1× as much) and $0.525 for Qwen2.5-VL 7B Instruct (1.2× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. ERNIE 4.5 300B A47B has not been scored yet, Qwen2.5-VL 7B Instruct has not been scored yet and Codestral 25.08 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for ERNIE 4.5 300B A47B, Qwen2.5-VL 7B Instruct and Codestral 25.08 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
ERNIE 4.5 300B A47B and Qwen2.5-VL 7B Instruct have the largest context windows (131,072 and 131,072 tokens), against 128,000 for Codestral 25.08. Maximum output per response: ERNIE 4.5 300B A47B up to 12,000, Qwen2.5-VL 7B Instruct up to 8,192, Codestral 25.08 up to 8,192 tokens.
Which can read images, PDFs, audio or video?
ERNIE 4.5 300B A47B accepts text; Qwen2.5-VL 7B Instruct accepts text and images; Codestral 25.08 accepts text. Qwen2.5-VL 7B Instruct handles the widest range of inputs.
Are any of these open source?
ERNIE 4.5 300B A47B and Qwen2.5-VL 7B Instruct publishes its weights (Apache-2.0) and can be self-hosted; Codestral 25.08 is proprietary.
Which is newer?
Codestral 25.08 is the newest, released Jul 30, 2025. ERNIE 4.5 300B A47B came out Jun 30, 2025; Qwen2.5-VL 7B Instruct came out Sep 2024. Knowledge cutoff: Qwen2.5-VL 7B Instruct Apr 2024.
How do you decide the winner?
This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, 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.