Claude Haiku 3.5 vs Llama-3.3-70B-Instruct vs Nova Pro
Too close to call on our weighted score (Nova Pro 49, Claude Haiku 3.5 49, Llama-3.3-70B-Instruct 41). The right pick depends on what you value most.
AnthropicClaude Haiku 3.5
49/100- ECI127.2
- Price—
- Context200K
MetaLlama-3.3-70B-Instruct
41/100- ECI127.3
- Price$0.59 / $0.724
- Context128K
AmazonNova Pro
49/100- ECI123.8
- Price$0.80 / $3.20
- Context300K
Too close to call
It is close. Our weighted score puts them within a point (Nova Pro 49/100, Claude Haiku 3.5 49/100, Llama-3.3-70B-Instruct 41/100), so choose by what matters most for your work: Llama-3.3-70B-Instruct for raw capability and Nova Pro for long inputs. The score weighs capability 67%, inputs & features 20%, context window 13%.
- CapabilityLlama-3.3-70B-InstructCapabilities Index (ECI): Llama-3.3-70B-Instruct 127.3 · Claude Haiku 3.5 127.2 · Nova Pro 123.8
- Lowest priceLlama-3.3-70B-InstructLlama-3.3-70B-Instruct $0.624 · Nova Pro $1.40 per 1M tokens (3:1 blend) · Claude Haiku 3.5 unpriced
- Longest contextNova ProNova Pro 300,000 · Claude Haiku 3.5 200,000 · Llama-3.3-70B-Instruct 128,000 tokens
- Widest inputsNova ProClaude Haiku 3.5: Text, Images, PDFs · Llama-3.3-70B-Instruct: Text · Nova Pro: Text, Images, PDFs, Video
- Self-hostingLlama-3.3-70B-InstructPublishes downloadable weights
| Measure | Weight | Claude Haiku 3.5 | Llama-3.3-70B-Instruct | Nova Pro |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 67% | 49 | 49 | 45 |
| Inputs & features | 20% | 60 | 25 | 70 |
| Context window | 13% | 32 | 24 | 39 |
| Overall | 100% | 49/100 | 41/100 | 49/100 |
Left out because at least one model lacks the data: price. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Claude Haiku 3.5Anthropic | Llama-3.3-70B-InstructMeta | Nova ProAmazon |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 127.2 | 127.3 (best) | 123.8 |
| ECI rank | #134 of 148 | #133 of 148 (best) | #137 of 148 |
| GPQA DiamondGraduate-level science questions | 38.1% | 47.4% (best) | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 4.3% | 5.1% (best) | — |
| Price per million tokens | |||
| Input | — | $0.59 (best) | $0.80 |
| Output | — | $0.724 (best) | $3.20 |
| Cached input | — | — | $0.20 |
| Blended (3:1) | — | $0.624 (best) | $1.40 |
| Long-context rate | — | Same rate | Same rate |
| Price source | — | Median of 21 providers | Official Amazon Bedrock API |
| Limits | |||
| Context window | 200,000 tokens | 128,000 tokens | 300,000 tokens (best) |
| Max output | 8,192 tokens | 4,096 tokens | 10,000 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | Yes |
| PDFs | Yes | No | Yes |
| Audio | No | No | No |
| Video | No | No | Yes |
| Reasoning | No | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Proprietary | Open | Proprietary |
| API model ID | — | llama-3.3-70b-instruct | amazon.nova-pro-v1:0 |
| API providers | — | 24 (best) | 3 |
| Released | Oct 22, 2024 | Dec 6, 2024 | Dec 3, 2024 |
| Knowledge cutoff | Jul 31, 2024 | Dec 2023 | Oct 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—
- Llama-3.3-70B-Instruct$7.35
- Nova Pro$14.40
Which should you choose?
Which is better: Claude Haiku 3.5, Llama-3.3-70B-Instruct or Nova Pro?
It is close. Our weighted score puts them within a point (Nova Pro 49/100, Claude Haiku 3.5 49/100, Llama-3.3-70B-Instruct 41/100), so choose by what matters most for your work: Llama-3.3-70B-Instruct for raw capability and Nova Pro for long inputs. The score weighs capability 67%, inputs & features 20%, context window 13%.
Which is cheaper, Claude Haiku 3.5, Llama-3.3-70B-Instruct or Nova Pro?
Llama-3.3-70B-Instruct is cheaper at $0.59 input / $0.724 output per million tokens (median across 21 API providers; free on Llama). Nova Pro costs $0.80 input / $3.20 output per million tokens (official Amazon Bedrock API price). At a typical mix of three input tokens to one output token, that is $0.624 per million tokens for Llama-3.3-70B-Instruct versus $1.40 for Nova Pro (2.2× as much). Claude Haiku 3.5 has no published per-token price.
Which scores higher on benchmarks?
Llama-3.3-70B-Instruct scores higher on the Capabilities Index (ECI): Llama-3.3-70B-Instruct 127.3 (#133 of 148), Claude Haiku 3.5 127.2 (#134 of 148) and Nova Pro 123.8 (#137 of 148). The confidence ranges of the top two overlap (122.5–129.5 vs 120.7–129.7), so treat the gap as small.
Which is better for coding?
There are no published SWE-bench Verified results for Claude Haiku 3.5, Llama-3.3-70B-Instruct and Nova Pro yet, so there is no like-for-like coding score. On overall capability, Llama-3.3-70B-Instruct leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.
Which has the bigger context window?
Nova Pro has the largest context window at 300,000 tokens, against 200,000 for Claude Haiku 3.5 and 128,000 for Llama-3.3-70B-Instruct. Maximum output per response: Claude Haiku 3.5 up to 8,192, Llama-3.3-70B-Instruct up to 4,096, Nova Pro up to 10,000 tokens.
Which can read images, PDFs, audio or video?
Claude Haiku 3.5 accepts text, images and PDFs; Llama-3.3-70B-Instruct accepts text; Nova Pro accepts text, images, PDFs and video. Nova Pro handles the widest range of inputs.
Are any of these open source?
Llama-3.3-70B-Instruct publishes its weights and can be self-hosted; Claude Haiku 3.5 and Nova Pro is proprietary.
Which is newer?
Llama-3.3-70B-Instruct is the newest, released Dec 6, 2024. Nova Pro came out Dec 3, 2024; Claude Haiku 3.5 came out Oct 22, 2024. Knowledge cutoff: Claude Haiku 3.5 Jul 31, 2024, Llama-3.3-70B-Instruct Dec 2023, Nova Pro Oct 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 Oct 4, 2026.
Related comparisons
- Claude Haiku 3.5 vs Mistral Large 2.1Mistral AI · ECI 128.5
- Claude Haiku 3.5 vs Qwen2.5 32B InstructAlibaba (Qwen) · ECI 128.5
- Claude Haiku 3.5 vs GPT-4o miniOpenAI · ECI 126.6
- Llama-3.3-70B-Instruct vs Mistral Small 3.1 24BMistral AI · ECI 127.5
- Llama-3.3-70B-Instruct vs Qwen2.5 32B InstructAlibaba (Qwen) · ECI 128.5
- Llama-3.3-70B-Instruct vs DeepSeek-V3DeepSeek · ECI 132.3
