Gemma 2 27B vs Aion-RP 1.0 (8B) vs Claude Haiku 3
No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.
Price in rating: Included · Exclude price
Google
Gemma 2 27B
28/100- ECI118.6
- Price$0.65 / $0.65
- Context8K
Aion Labs
Aion-RP 1.0 (8B)
26/100- ECI—
- Price$0.80 / $1.60
- Context33K
Anthropic
Claude Haiku 3
57/100- ECI117.8
- Price$0.25 / $1.25
- Context200K
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (Claude Haiku 3 57/100, Gemma 2 27B 28/100, Aion-RP 1.0 (8B) 26/100) 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 priceClaude Haiku 3Claude Haiku 3 $0.50 · Gemma 2 27B $0.65 · Aion-RP 1.0 (8B) $1.00 per 1M tokens (3:1 blend)
- Longest contextClaude Haiku 3Claude Haiku 3 200,000 · Aion-RP 1.0 (8B) 32,768 · Gemma 2 27B 8,192 tokens
- Widest inputsClaude Haiku 3Gemma 2 27B: Text · Aion-RP 1.0 (8B): Text · Claude Haiku 3: Text, Images, PDFs
- Self-hostingGemma 2 27B and Aion-RP 1.0 (8B)Publishes downloadable weights
| Measure | Weight | Gemma 2 27B | Aion-RP 1.0 (8B) | Claude Haiku 3 |
|---|---|---|---|---|
| Price | 50% | 56 | 48 | 61 |
| Inputs & features | 30% | 0 | 0 | 60 |
| Context window | 20% | 0 | 11 | 39 |
| Specs & price only | 100% | 28/100 | 26/100 | 57/100 |
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 | Aion-RP 1.0 (8B)Aion Labs | ||
|---|---|---|---|
| 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% |
| OTIS Mock AIME 2024–2025Competition mathematics | 1.4% | — | 1.8% (best) |
| Price per million tokens | |||
| Input | $0.65 | $0.80 | $0.25 (best) |
| Output | $0.65 (best) | $1.60 | $1.25 |
| Cached input | — | — | — |
| Blended (3:1) | $0.65 | $1.00 | $0.50 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 3 providers | Median of 4 providers | Median of 3 providers |
| Limits | |||
| Context window | 8,192 tokens | 32,768 tokens | 200,000 tokens (best) |
| Max output | 2,048 tokens | 29,491 tokens (best) | 4,096 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | Yes |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | No | No | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Open | Proprietary |
| API model ID | — | — | — |
| API providers | 3 | 4 (best) | 3 |
| Released | Jul 13, 2024 | Feb 4, 2025 | Mar 13, 2024 |
| Knowledge cutoff | Jun 30, 2024 | Dec 31, 2023 | 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
- Aion-RP 1.0 (8B)$11.20
Claude Haiku 3$5.00
Which should you choose?
Which is better: Gemma 2 27B, Aion-RP 1.0 (8B) or Claude Haiku 3?
There is not enough shared capability evidence to name an overall winner. The scores (Claude Haiku 3 57/100, Gemma 2 27B 28/100, Aion-RP 1.0 (8B) 26/100) 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, Gemma 2 27B, Aion-RP 1.0 (8B) or Claude Haiku 3?
Claude Haiku 3 is cheaper at $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); Aion-RP 1.0 (8B) costs $0.80 input / $1.60 output per million tokens (median across 4 API providers). At a typical mix of three input tokens to one output token, that is $0.50 per million tokens for Claude Haiku 3 versus $0.65 for Gemma 2 27B (1.3× as much) and $1.00 for Aion-RP 1.0 (8B) (2× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Gemma 2 27B has an ECI of 118.6, Aion-RP 1.0 (8B) has not been scored yet and Claude Haiku 3 has an ECI of 117.8.
Which is better for coding?
There are no published SWE-bench Verified results for Gemma 2 27B, Aion-RP 1.0 (8B) and Claude Haiku 3 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Gemma 2 27B and Aion-RP 1.0 (8B) 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 32,768 for Aion-RP 1.0 (8B) and 8,192 for Gemma 2 27B. Maximum output per response: Gemma 2 27B up to 2,048, Aion-RP 1.0 (8B) up to 29,491, Claude Haiku 3 up to 4,096 tokens.
Which can read images, PDFs, audio or video?
Gemma 2 27B accepts text; Aion-RP 1.0 (8B) accepts text; Claude Haiku 3 accepts text, images and PDFs. Claude Haiku 3 handles the widest range of inputs.
Are any of these open source?
Gemma 2 27B and Aion-RP 1.0 (8B) publishes its weights and can be self-hosted; Claude Haiku 3 is proprietary.
Which is newer?
Aion-RP 1.0 (8B) is the newest, released Feb 4, 2025. Gemma 2 27B came out Jul 13, 2024; Claude Haiku 3 came out Mar 13, 2024. Knowledge cutoff: Gemma 2 27B Jun 30, 2024, Aion-RP 1.0 (8B) Dec 31, 2023, Claude Haiku 3 Aug 31, 2023.
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.