Codestral 25.08 vs ERNIE 4.5 300B A47B vs Llama 3.3 Nemotron Super 49B v1.5
Too close to call on our weighted score (Llama 3.3 Nemotron Super 49B v1.5 48, Codestral 25.08 47, ERNIE 4.5 300B A47B 43). The right pick depends on what you value most.
Mistral AICodestral 25.08
47/100- ECI—
- Price$0.30 / $0.90
- Context128K
BaiduERNIE 4.5 300B A47B
43/100- ECI—
- Price$0.28 / $1.10
- Context131K
NVIDIALlama 3.3 Nemotron Super 49B v1.5
48/100- ECI—
- Price$0.40 / $0.40
- Context131K
Too close to call
It is close. Our weighted score puts them within 1 points (Llama 3.3 Nemotron Super 49B v1.5 48/100, Codestral 25.08 47/100, ERNIE 4.5 300B A47B 43/100), so choose by what matters most for your work: Llama 3.3 Nemotron Super 49B v1.5 on 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 priceLlama 3.3 Nemotron Super 49B v1.5Llama 3.3 Nemotron Super 49B v1.5 $0.40 · Codestral 25.08 $0.45 · ERNIE 4.5 300B A47B $0.485 per 1M tokens (3:1 blend)
- Longest contextERNIE 4.5 300B A47B and Llama 3.3 Nemotron Super 49B v1.5ERNIE 4.5 300B A47B 131,072 · Llama 3.3 Nemotron Super 49B v1.5 131,072 · Codestral 25.08 128,000 tokens
- Widest inputsSame inputsCodestral 25.08: Text · ERNIE 4.5 300B A47B: Text · Llama 3.3 Nemotron Super 49B v1.5: Text
- Self-hostingERNIE 4.5 300B A47B and Llama 3.3 Nemotron Super 49B v1.5Publishes downloadable weights (Apache-2.0)
| Measure | Weight | Codestral 25.08 | ERNIE 4.5 300B A47B | Llama 3.3 Nemotron Super 49B v1.5 |
|---|---|---|---|---|
| Price | 50% | 64 | 62 | 66 |
| Inputs & features | 30% | 35 | 25 | 35 |
| Context window | 20% | 24 | 25 | 25 |
| Overall | 100% | 47/100 | 43/100 | 48/100 |
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 | Codestral 25.08Mistral AI | ERNIE 4.5 300B A47BBaidu | Llama 3.3 Nemotron Super 49B v1.5NVIDIA |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.30 | $0.28 (best) | $0.40 |
| Output | $0.90 | $1.10 | $0.40 (best) |
| Cached input | $0.03 | — | — |
| Blended (3:1) | $0.45 | $0.485 | $0.40 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Mistral API | Median of 1 providers | Median of 1 providers |
| Limits | |||
| Context window | 128,000 tokens | 131,072 tokens (best) | 131,072 tokens (best) |
| Max output | 8,192 tokens | 12,000 tokens | 131,072 tokens (best) |
| 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 | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Proprietary | OpenApache-2.0 | Open |
| API model ID | codestral-2508 | — | — |
| API providers | 11 (best) | 1 | 1 |
| Released | Jul 30, 2025 | Jun 30, 2025 | Jul 25, 2025 |
| Knowledge cutoff | — | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Codestral 25.08$4.80
- ERNIE 4.5 300B A47B$5.00
- Llama 3.3 Nemotron Super 49B v1.5$4.80
Which should you choose?
Which is better: Codestral 25.08, ERNIE 4.5 300B A47B or Llama 3.3 Nemotron Super 49B v1.5?
It is close. Our weighted score puts them within 1 points (Llama 3.3 Nemotron Super 49B v1.5 48/100, Codestral 25.08 47/100, ERNIE 4.5 300B A47B 43/100), so choose by what matters most for your work: Llama 3.3 Nemotron Super 49B v1.5 on 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, Codestral 25.08, ERNIE 4.5 300B A47B or Llama 3.3 Nemotron Super 49B v1.5?
Llama 3.3 Nemotron Super 49B v1.5 is cheaper at $0.40 input / $0.40 output per million tokens (median across 1 API provider). Codestral 25.08 costs $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). At a typical mix of three input tokens to one output token, that is $0.40 per million tokens for Llama 3.3 Nemotron Super 49B v1.5 versus $0.45 for Codestral 25.08 (1.1× as much) and $0.485 for ERNIE 4.5 300B A47B (1.2× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Codestral 25.08 has not been scored yet, ERNIE 4.5 300B A47B has not been scored yet and Llama 3.3 Nemotron Super 49B v1.5 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Codestral 25.08, ERNIE 4.5 300B A47B and Llama 3.3 Nemotron Super 49B v1.5 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 Llama 3.3 Nemotron Super 49B v1.5 have the largest context windows (131,072 and 131,072 tokens), against 128,000 for Codestral 25.08. Maximum output per response: Codestral 25.08 up to 8,192, ERNIE 4.5 300B A47B up to 12,000, Llama 3.3 Nemotron Super 49B v1.5 up to 131,072 tokens.
Which can read images, PDFs, audio or video?
Codestral 25.08 accepts text; ERNIE 4.5 300B A47B accepts text; Llama 3.3 Nemotron Super 49B v1.5 accepts text. They handle the same number of input types.
Are any of these open source?
ERNIE 4.5 300B A47B and Llama 3.3 Nemotron Super 49B v1.5 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. Llama 3.3 Nemotron Super 49B v1.5 came out Jul 25, 2025; ERNIE 4.5 300B A47B came out Jun 30, 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 Nov 2, 2026.
Related comparisons
- Codestral 25.08 vs GLM-4.5-AirZ.ai (Zhipu)
- Codestral 25.08 vs Qwen3 Omni 30B A3B ThinkingAlibaba (Qwen)
- ERNIE 4.5 300B A47B vs GLM-4.5-AirZ.ai (Zhipu)
- ERNIE 4.5 300B A47B vs Grok Code Fast 1xAI
- Llama 3.3 Nemotron Super 49B v1.5 vs GLM-4.5-AirZ.ai (Zhipu)
- Llama 3.3 Nemotron Super 49B v1.5 vs Gemma-SEA-LION-v4-27B-ITAI Singapore
