Claude Haiku 3 vs Llama-3.1-70B-Instruct vs Gemma 2 27B
Claude Haiku 3 comes out ahead, 52 to 47 and 38 on our weighted score, and it is the cheaper option too.
Price in rating: Included · Exclude price
- Our pick
Anthropic
Claude Haiku 3
52/100- ECI117.8
- Price$0.25 / $1.25
- Context200K
Meta
Llama-3.1-70B-Instruct
47/100- ECI124.7
- Price$0.72 / $0.72
- Context128K
Google
Gemma 2 27B
38/100- ECI118.6
- Price$0.65 / $0.65
- Context8K
Claude Haiku 3 is our pick
Claude Haiku 3 is the better all-round choice, scoring 52/100 against Llama-3.1-70B-Instruct (47) and Gemma 2 27B (38). It leads on price, inputs & features and context window. Llama-3.1-70B-Instruct wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityLlama-3.1-70B-InstructCapabilities Index (ECI): Llama-3.1-70B-Instruct 124.7 · Gemma 2 27B 118.6 · Claude Haiku 3 117.8
- Lowest priceClaude Haiku 3Claude Haiku 3 $0.50 · Gemma 2 27B $0.65 · Llama-3.1-70B-Instruct $0.72 per 1M tokens (3:1 blend)
- Longest contextClaude Haiku 3Claude Haiku 3 200,000 · Llama-3.1-70B-Instruct 128,000 · Gemma 2 27B 8,192 tokens
- Widest inputsClaude Haiku 3Claude Haiku 3: Text, Images, PDFs · Llama-3.1-70B-Instruct: Text · Gemma 2 27B: Text
- Self-hostingLlama-3.1-70B-Instruct and Gemma 2 27BPublishes downloadable weights
| Measure | Weight | Claude Haiku 3 | Llama-3.1-70B-Instruct | Gemma 2 27B |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 47 | 53 | 48 |
| Price | 25% | 61 | 54 | 56 |
| Inputs & features | 15% | 60 | 25 | 0 |
| Context window | 10% | 39 | 32 | 0 |
| Overall | 100% | 52/100 | 47/100 | 38/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 117.8 | 124.7 (best) | 118.6 |
| ECI rank | #154 of 158 | #146 of 158 (best) | #152 of 158 |
| GPQA DiamondGraduate-level science questions | 36.3% | 44.2% (best) | 36.5% |
| OTIS Mock AIME 2024–2025Competition mathematics | 1.8% | 3.6% (best) | 1.4% |
| Price per million tokens | |||
| Input | $0.25 (best) | $0.72 | $0.65 |
| Output | $1.25 | $0.72 | $0.65 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.50 (best) | $0.72 | $0.65 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 3 providers | Median of 7 providers | Median of 3 providers |
| Limits | |||
| Context window | 200,000 tokens (best) | 128,000 tokens | 8,192 tokens |
| Max output | 4,096 tokens (best) | 4,096 tokens (best) | 2,048 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | Yes | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | Yes | Yes | No |
| Structured output | No | No | No |
| Availability | |||
| Weights | Proprietary | Open | Open |
| API model ID | — | — | — |
| API providers | 3 | 7 (best) | 3 |
| Released | Mar 13, 2024 | Jul 23, 2024 | Jul 13, 2024 |
| Knowledge cutoff | Aug 31, 2023 | Dec 2023 | 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.
Claude Haiku 3$5.00
Llama-3.1-70B-Instruct$8.64
Gemma 2 27B$7.80
Which should you choose?
Which is better: Claude Haiku 3, Llama-3.1-70B-Instruct or Gemma 2 27B?
Claude Haiku 3 is the better all-round choice, scoring 52/100 against Llama-3.1-70B-Instruct (47) and Gemma 2 27B (38). It leads on price, inputs & features and context window. Llama-3.1-70B-Instruct wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, Claude Haiku 3, Llama-3.1-70B-Instruct or Gemma 2 27B?
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); Llama-3.1-70B-Instruct costs $0.72 input / $0.72 output per million tokens (median across 7 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 $0.72 for Llama-3.1-70B-Instruct (1.4× as much).
Which scores higher on benchmarks?
Llama-3.1-70B-Instruct scores higher on the Capabilities Index (ECI): Llama-3.1-70B-Instruct 124.7 (#146 of 158), Gemma 2 27B 118.6 (#152 of 158) and Claude Haiku 3 117.8 (#154 of 158). The confidence ranges of the top two overlap (121.6–127.6 vs 114.5–122.4), so treat the gap as small. On individual benchmarks: GPQA Diamond — Llama-3.1-70B-Instruct 44.2%, Gemma 2 27B 36.5%, Claude Haiku 3 36.3%; OTIS Mock AIME 2024–2025 — Llama-3.1-70B-Instruct 3.6%, Claude Haiku 3 1.8%, Gemma 2 27B 1.4%.
Which is better for coding?
There are no published SWE-bench Verified results for Claude Haiku 3, Llama-3.1-70B-Instruct and Gemma 2 27B yet, so there is no like-for-like coding score. On overall capability, Llama-3.1-70B-Instruct 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 128,000 for Llama-3.1-70B-Instruct and 8,192 for Gemma 2 27B. Maximum output per response: Claude Haiku 3 up to 4,096, Llama-3.1-70B-Instruct up to 4,096, Gemma 2 27B up to 2,048 tokens.
Which can read images, PDFs, audio or video?
Claude Haiku 3 accepts text, images and PDFs; Llama-3.1-70B-Instruct accepts text; Gemma 2 27B accepts text. Claude Haiku 3 handles the widest range of inputs.
Are any of these open source?
Llama-3.1-70B-Instruct and Gemma 2 27B publishes its weights and can be self-hosted; Claude Haiku 3 is proprietary.
Which is newer?
Llama-3.1-70B-Instruct is the newest, released Jul 23, 2024. Gemma 2 27B came out Jul 13, 2024; Claude Haiku 3 came out Mar 13, 2024. Knowledge cutoff: Claude Haiku 3 Aug 31, 2023, Llama-3.1-70B-Instruct Dec 2023, Gemma 2 27B Jun 30, 2024.
How do you decide the winner?
This rating uses 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 18, 2026.