Claude Haiku 3.5 vs Llama-3.2-90B-Vision-Instruct vs Claude Sonnet 3.5 v2
Claude Sonnet 3.5 v2 comes out ahead, 54 to 48 and 44 on our weighted score, though Claude Haiku 3.5 is 3.5× cheaper per token.
AnthropicClaude Haiku 3.5
48/100- ECI127.0
- Price$0.80 / $4.00
- Context200K
MetaLlama-3.2-90B-Vision-Instruct
44/100- ECI125.5
- Price—
- Context128K
- Our pickAnthropic
Claude Sonnet 3.5 v2
54/100- ECI133.4
- Price$2.80 / $14.00
- Context200K
Claude Sonnet 3.5 v2 is our pick
Claude Sonnet 3.5 v2 is the better all-round choice, scoring 54/100 against Claude Haiku 3.5 (48) and Llama-3.2-90B-Vision-Instruct (44). It leads on capability. The score weighs capability 67%, inputs & features 20%, context window 13%.
- CapabilityClaude Sonnet 3.5 v2Capabilities Index (ECI): Claude Sonnet 3.5 v2 133.4 · Claude Haiku 3.5 127.0 · Llama-3.2-90B-Vision-Instruct 125.5
- Lowest priceClaude Haiku 3.5Claude Haiku 3.5 $1.60 · Claude Sonnet 3.5 v2 $5.60 per 1M tokens (3:1 blend) · Llama-3.2-90B-Vision-Instruct unpriced
- Longest contextClaude Haiku 3.5 and Claude Sonnet 3.5 v2Claude Haiku 3.5 200,000 · Claude Sonnet 3.5 v2 200,000 · Llama-3.2-90B-Vision-Instruct 128,000 tokens
- Widest inputsClaude Haiku 3.5 and Claude Sonnet 3.5 v2Claude Haiku 3.5: Text, Images, PDFs · Llama-3.2-90B-Vision-Instruct: Text, Images · Claude Sonnet 3.5 v2: Text, Images, PDFs
- Self-hostingLlama-3.2-90B-Vision-InstructPublishes downloadable weights (Llama 3.2 Community License)
| Measure | Weight | Claude Haiku 3.5 | Llama-3.2-90B-Vision-Instruct | Claude Sonnet 3.5 v2 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 67% | 48 | 46 | 56 |
| Inputs & features | 20% | 60 | 50 | 60 |
| Context window | 13% | 32 | 24 | 32 |
| Overall | 100% | 48/100 | 44/100 | 54/100 |
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-3.2-90B-Vision-InstructMeta | Claude Sonnet 3.5 v2Anthropic |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 127.0 | 125.5 | 133.4 (best) |
| ECI rank | #147 of 165 | #150 of 165 | #133 of 165 (best) |
| GPQA DiamondGraduate-level science questions | 38.1% | 41.0% | 55.3% (best) |
| OTIS Mock AIME 2024–2025Competition mathematics | 4.3% | 2.6% | 8.5% (best) |
| Price per million tokens | |||
| Input | $0.80 (best) | — | $2.80 |
| Output | $4.00 (best) | — | $14.00 |
| Cached input | — | — | — |
| Blended (3:1) | $1.60 (best) | — | $5.60 |
| Long-context rate | Same rate | — | Same rate |
| Price source | Median of 3 providers | — | Median of 2 providers |
| Limits | |||
| Context window | 200,000 tokens (best) | 128,000 tokens | 200,000 tokens (best) |
| Max output | 8,192 tokens (best) | 4,096 tokens | 8,192 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | Yes | No | Yes |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Proprietary | OpenLlama 3.2 Community License | Proprietary |
| API model ID | — | — | — |
| API providers | 4 (best) | 1 | 3 |
| Released | Oct 22, 2024 | Sep 25, 2024 | Oct 22, 2024 |
| Knowledge cutoff | Jul 31, 2024 | Dec 2023 | Apr 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$16.00
- Llama-3.2-90B-Vision-Instruct—
- Claude Sonnet 3.5 v2$56.00
Which should you choose?
Which is better: Claude Haiku 3.5, Llama-3.2-90B-Vision-Instruct or Claude Sonnet 3.5 v2?
Claude Sonnet 3.5 v2 is the better all-round choice, scoring 54/100 against Claude Haiku 3.5 (48) and Llama-3.2-90B-Vision-Instruct (44). It leads on capability. The score weighs capability 67%, inputs & features 20%, context window 13%.
Which is cheaper, Claude Haiku 3.5, Llama-3.2-90B-Vision-Instruct or Claude Sonnet 3.5 v2?
Claude Haiku 3.5 is cheaper at $0.80 input / $4.00 output per million tokens (median across 3 API providers). Claude Sonnet 3.5 v2 costs $2.80 input / $14.00 output per million tokens (median across 2 API providers). At a typical mix of three input tokens to one output token, that is $1.60 per million tokens for Claude Haiku 3.5 versus $5.60 for Claude Sonnet 3.5 v2 (3.5× as much). Llama-3.2-90B-Vision-Instruct has no published per-token price.
Which scores higher on benchmarks?
Claude Sonnet 3.5 v2 scores higher on the Capabilities Index (ECI): Claude Sonnet 3.5 v2 133.4 (#133 of 165), Claude Haiku 3.5 127.0 (#147 of 165) and Llama-3.2-90B-Vision-Instruct 125.5 (#150 of 165). The confidence ranges of the top two overlap (128.5–137.7 vs 121.4–129.2), so treat the gap as small. On individual benchmarks: GPQA Diamond — Claude Sonnet 3.5 v2 55.3%, Llama-3.2-90B-Vision-Instruct 41.0%, Claude Haiku 3.5 38.1%; OTIS Mock AIME 2024–2025 — Claude Sonnet 3.5 v2 8.5%, Claude Haiku 3.5 4.3%, Llama-3.2-90B-Vision-Instruct 2.6%.
Which is better for coding?
There are no published SWE-bench Verified results for Claude Haiku 3.5, Llama-3.2-90B-Vision-Instruct and Claude Sonnet 3.5 v2 yet, so there is no like-for-like coding score. On overall capability, Claude Sonnet 3.5 v2 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?
Claude Haiku 3.5 and Claude Sonnet 3.5 v2 have the largest context windows (200,000 and 200,000 tokens), against 128,000 for Llama-3.2-90B-Vision-Instruct. Maximum output per response: Claude Haiku 3.5 up to 8,192, Llama-3.2-90B-Vision-Instruct up to 4,096, Claude Sonnet 3.5 v2 up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Claude Haiku 3.5 accepts text, images and PDFs; Llama-3.2-90B-Vision-Instruct accepts text and images; Claude Sonnet 3.5 v2 accepts text, images and PDFs. Claude Haiku 3.5 handles the widest range of inputs.
Are any of these open source?
Llama-3.2-90B-Vision-Instruct publishes its weights (Llama 3.2 Community License) and can be self-hosted; Claude Haiku 3.5 and Claude Sonnet 3.5 v2 is proprietary.
Which is newer?
Claude Haiku 3.5 is the newest, released Oct 22, 2024. Claude Sonnet 3.5 v2 came out Oct 22, 2024; Llama-3.2-90B-Vision-Instruct came out Sep 25, 2024. Knowledge cutoff: Claude Haiku 3.5 Jul 31, 2024, Llama-3.2-90B-Vision-Instruct Dec 2023, Claude Sonnet 3.5 v2 Apr 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.
Related comparisons
- Claude Haiku 3.5 vs Mistral Large 2.1Mistral AI · ECI 128.6
- Claude Haiku 3.5 vs Llama-3.3-70B-InstructMeta · ECI 127.3
- Claude Haiku 3.5 vs GPT-4oOpenAI · ECI 129.0
- Claude Haiku 3.5 vs Gemma 2 27BGoogle · ECI 122.1
- Llama-3.2-90B-Vision-Instruct vs GPT-4o miniOpenAI · ECI 126.5
- Llama-3.2-90B-Vision-Instruct vs Mistral Large 2407Mistral AI · ECI 127.6
