Gemma 2 27B vs Claude Haiku 3 vs Qwen2.5 7B Instruct
Claude Haiku 3 comes out ahead, 30 to 22 and 13 on our weighted score, though Qwen2.5 7B Instruct is 5.3× cheaper per token.
Price in rating: Excluded · Include price
Google
Gemma 2 27B
13/100- ECI118.6
- Price$0.65 / $0.65
- Context8K
- Our pick
Anthropic
Claude Haiku 3
30/100- ECI117.8
- Price$0.25 / $1.25
- Context200K
Alibaba (Qwen)
Qwen2.5 7B Instruct
22/100- ECI—
- Price$0.075 / $0.15
- Context131K
Claude Haiku 3 is our pick
Claude Haiku 3 is the better all-round choice, scoring 30/100 against Qwen2.5 7B Instruct (22) and Gemma 2 27B (13). It leads on inputs & features and context window. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because Qwen2.5 7B Instruct has no Capabilities Index score yet.
- CapabilityClaude Haiku 3Shared benchmarks: Claude Haiku 3 19.1% · Qwen2.5 7B Instruct 19.0% · Gemma 2 27B 18.9%
- Lowest priceQwen2.5 7B InstructQwen2.5 7B Instruct $0.094 · Claude Haiku 3 $0.50 · Gemma 2 27B $0.65 per 1M tokens (3:1 blend)
- Longest contextClaude Haiku 3Claude Haiku 3 200,000 · Qwen2.5 7B Instruct 131,072 · Gemma 2 27B 8,192 tokens
- Widest inputsClaude Haiku 3Gemma 2 27B: Text · Claude Haiku 3: Text, Images, PDFs · Qwen2.5 7B Instruct: Text
- Self-hostingGemma 2 27B and Qwen2.5 7B InstructPublishes downloadable weights (Apache 2.0)
| Measure | Weight | Gemma 2 27B | Claude Haiku 3 | Qwen2.5 7B Instruct |
|---|---|---|---|---|
| CapabilityShared benchmarks | 67% | 19 | 19 | 19 |
| Inputs & features | 20% | 0 | 60 | 25 |
| Context window | 13% | 0 | 39 | 32 |
| Overall | 100% | 13/100 | 30/100 | 22/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 118.6 (best) | 117.8 | — |
| ECI rank | #152 of 158 (best) | #154 of 158 | — |
| GPQA DiamondGraduate-level science questions | 36.5% (best) | 36.3% | 35.5% |
| OTIS Mock AIME 2024–2025Competition mathematics | 1.4% | 1.8% | 2.5% (best) |
| Price per million tokens | |||
| Input | $0.65 | $0.25 | $0.075 (best) |
| Output | $0.65 | $1.25 | $0.15 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.65 | $0.50 | $0.094 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 3 providers | Median of 3 providers | Median of 4 providers |
| Limits | |||
| Context window | 8,192 tokens | 200,000 tokens (best) | 131,072 tokens |
| Max output | 2,048 tokens | 4,096 tokens | 8,192 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | Yes | 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 | Open | Proprietary | OpenApache 2.0 |
| API model ID | — | — | — |
| API providers | 3 | 3 | 5 (best) |
| Released | Jul 13, 2024 | Mar 13, 2024 | Sep 19, 2024 |
| Knowledge cutoff | Jun 30, 2024 | Aug 31, 2023 | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Gemma 2 27B$7.80
Claude Haiku 3$5.00
Qwen2.5 7B Instruct$1.05
Which should you choose?
Which is better: Gemma 2 27B, Claude Haiku 3 or Qwen2.5 7B Instruct?
Claude Haiku 3 is the better all-round choice, scoring 30/100 against Qwen2.5 7B Instruct (22) and Gemma 2 27B (13). It leads on inputs & features and context window. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because Qwen2.5 7B Instruct has no Capabilities Index score yet.
Which is cheaper, Gemma 2 27B, Claude Haiku 3 or Qwen2.5 7B Instruct?
Qwen2.5 7B Instruct is cheaper at $0.075 input / $0.15 output per million tokens (median across 4 API providers). Claude Haiku 3 costs $0.25 input / $1.25 output per million tokens (median across 3 API providers); Gemma 2 27B costs $0.65 input / $0.65 output per million tokens (median across 3 API providers). At a typical mix of three input tokens to one output token, that is $0.094 per million tokens for Qwen2.5 7B Instruct versus $0.50 for Claude Haiku 3 (5.3× as much) and $0.65 for Gemma 2 27B (6.9× as much).
Which scores higher on benchmarks?
Not every model here has a Capabilities Index score, so we compare the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025): Claude Haiku 3 19.1%, Qwen2.5 7B Instruct 19.0% and Gemma 2 27B 18.9%. On individual benchmarks: GPQA Diamond — Gemma 2 27B 36.5%, Claude Haiku 3 36.3%, Qwen2.5 7B Instruct 35.5%; OTIS Mock AIME 2024–2025 — Qwen2.5 7B Instruct 2.5%, Claude Haiku 3 1.8%, Gemma 2 27B 1.4%.
Which is better for coding?
There are no published SWE-bench Verified results for Gemma 2 27B, Claude Haiku 3 and Qwen2.5 7B Instruct yet, so there is no like-for-like coding score. On overall capability, Claude Haiku 3 leads, which tends to carry over to coding, but test on your own codebase. Note that Gemma 2 27B does not support tool calling, which most coding agents need.
Which has the bigger context window?
Claude Haiku 3 has the largest context window at 200,000 tokens, against 131,072 for Qwen2.5 7B Instruct and 8,192 for Gemma 2 27B. Maximum output per response: Gemma 2 27B up to 2,048, Claude Haiku 3 up to 4,096, Qwen2.5 7B Instruct up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Gemma 2 27B accepts text; Claude Haiku 3 accepts text, images and PDFs; Qwen2.5 7B Instruct accepts text. Claude Haiku 3 handles the widest range of inputs.
Are any of these open source?
Gemma 2 27B and Qwen2.5 7B Instruct publishes its weights (Apache 2.0) and can be self-hosted; Claude Haiku 3 is proprietary.
Which is newer?
Qwen2.5 7B Instruct is the newest, released Sep 19, 2024. Gemma 2 27B came out Jul 13, 2024; Claude Haiku 3 came out Mar 13, 2024. Knowledge cutoff: Gemma 2 27B Jun 30, 2024, Claude Haiku 3 Aug 31, 2023.
How do you decide the winner?
This rating uses capability (67%, independent benchmark results); inputs & features (20%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (13%, 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.