Aya Expanse 32B vs Gemma 2 27B vs Qwen2.5-Coder-32B-Instruct
Qwen2.5-Coder-32B-Instruct comes out ahead, 39 to 32 and 28 on our weighted score, though Gemma 2 27B is 13% cheaper per token.
CohereAya Expanse 32B
32/100- ECI—
- Price$0.50 / $1.50
- Context128K
GoogleGemma 2 27B
28/100- ECI122.1
- Price$0.65 / $0.65
- Context8K
- Our pick
Alibaba (Qwen)Qwen2.5-Coder-32B-Instruct
39/100- ECI—
- Price$0.66 / $1.00
- Context131K
Qwen2.5-Coder-32B-Instruct is our pick
Qwen2.5-Coder-32B-Instruct is the better all-round choice, scoring 39/100 against Aya Expanse 32B (32) and Gemma 2 27B (28). It leads on inputs & features. Gemma 2 27B wins 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 priceGemma 2 27BGemma 2 27B $0.65 · Qwen2.5-Coder-32B-Instruct $0.745 · Aya Expanse 32B $0.75 per 1M tokens (3:1 blend)
- Longest contextQwen2.5-Coder-32B-InstructQwen2.5-Coder-32B-Instruct 131,072 · Aya Expanse 32B 128,000 · Gemma 2 27B 8,192 tokens
- Widest inputsSame inputsAya Expanse 32B: Text · Gemma 2 27B: Text · Qwen2.5-Coder-32B-Instruct: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Aya Expanse 32B | Gemma 2 27B | Qwen2.5-Coder-32B-Instruct |
|---|---|---|---|---|
| Price | 50% | 53 | 56 | 54 |
| Inputs & features | 30% | 0 | 0 | 25 |
| Context window | 20% | 24 | 0 | 25 |
| Overall | 100% | 32/100 | 28/100 | 39/100 |
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 | Aya Expanse 32BCohere | Gemma 2 27BGoogle | Qwen2.5-Coder-32B-InstructAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | 122.1 | — |
| ECI rank | — | #152 of 165 | — |
| GPQA DiamondGraduate-level science questions | — | 36.5% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 1.4% | — |
| Price per million tokens | |||
| Input | $0.50 (best) | $0.65 | $0.66 |
| Output | $1.50 | $0.65 (best) | $1.00 |
| Cached input | — | — | — |
| Blended (3:1) | $0.75 | $0.65 (best) | $0.745 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Cohere API | Median of 3 providers | Median of 7 providers |
| Limits | |||
| Context window | 128,000 tokens | 8,192 tokens | 131,072 tokens (best) |
| Max output | 4,000 tokens | 2,048 tokens | 8,192 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 | No |
| Tool calling | No | No | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | OpenCC-BY-NC-4.0 | Open | Open |
| API model ID | c4ai-aya-expanse-32b | — | — |
| API providers | 2 | 3 | 7 (best) |
| Released | Oct 24, 2024 | Jul 13, 2024 | Nov 12, 2024 |
| Knowledge cutoff | — | Jun 30, 2024 | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Aya Expanse 32B$8.00
- Gemma 2 27B$7.80
- Qwen2.5-Coder-32B-Instruct$8.60
Which should you choose?
Which is better: Aya Expanse 32B, Gemma 2 27B or Qwen2.5-Coder-32B-Instruct?
Qwen2.5-Coder-32B-Instruct is the better all-round choice, scoring 39/100 against Aya Expanse 32B (32) and Gemma 2 27B (28). It leads on inputs & features. Gemma 2 27B wins 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, Aya Expanse 32B, Gemma 2 27B or Qwen2.5-Coder-32B-Instruct?
Gemma 2 27B is cheaper at $0.65 input / $0.65 output per million tokens (median across 3 API providers). Qwen2.5-Coder-32B-Instruct costs $0.66 input / $1.00 output per million tokens (median across 7 API providers); Aya Expanse 32B costs $0.50 input / $1.50 output per million tokens (official Cohere API price). At a typical mix of three input tokens to one output token, that is $0.65 per million tokens for Gemma 2 27B versus $0.745 for Qwen2.5-Coder-32B-Instruct (1.1× as much) and $0.75 for Aya Expanse 32B (1.2× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Aya Expanse 32B has not been scored yet, Gemma 2 27B has an ECI of 122.1 and Qwen2.5-Coder-32B-Instruct has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Aya Expanse 32B, Gemma 2 27B and Qwen2.5-Coder-32B-Instruct yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Aya Expanse 32B and Gemma 2 27B does not support tool calling, which most coding agents need.
Which has the bigger context window?
Qwen2.5-Coder-32B-Instruct has the largest context window at 131,072 tokens, against 128,000 for Aya Expanse 32B and 8,192 for Gemma 2 27B. Maximum output per response: Aya Expanse 32B up to 4,000, Gemma 2 27B up to 2,048, Qwen2.5-Coder-32B-Instruct up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Aya Expanse 32B accepts text; Gemma 2 27B accepts text; Qwen2.5-Coder-32B-Instruct accepts text. They handle the same number of input types.
Are any of these open source?
Yes, all three publish their weights (CC-BY-NC-4.0), so you can self-host them.
Which is newer?
Qwen2.5-Coder-32B-Instruct is the newest, released Nov 12, 2024. Aya Expanse 32B came out Oct 24, 2024; Gemma 2 27B came out Jul 13, 2024. Knowledge cutoff: Gemma 2 27B Jun 30, 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 Nov 2, 2026.
