Sonar vs Claude Haiku 3 vs Qwen Plus Character (Japanese)
Claude Haiku 3 comes out ahead, 56 to 36 and 30 on our weighted score, and it is the cheaper option too.
PerplexitySonar
30/100- ECI—
- Price$1.00 / $1.00
- Context128K
- Our pick
AnthropicClaude Haiku 3
56/100- ECI118.4
- Price$0.25 / $1.25
- Context200K
Alibaba (Qwen)Qwen Plus Character (Japanese)
36/100- ECI—
- Price$0.50 / $1.40
- Context8K
Claude Haiku 3 is our pick
Claude Haiku 3 is the better all-round choice, scoring 56/100 against Qwen Plus Character (Japanese) (36) and Sonar (30). It leads on price, inputs & features and context window. 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 · Qwen Plus Character (Japanese) $0.725 · Sonar $1.00 per 1M tokens (3:1 blend)
- Longest contextClaude Haiku 3Claude Haiku 3 200,000 · Sonar 128,000 · Qwen Plus Character (Japanese) 8,192 tokens
- Widest inputsClaude Haiku 3Sonar: Text · Claude Haiku 3: Text, Images, PDFs · Qwen Plus Character (Japanese): Text
- Self-hostingNo open weightsAll three are available only through APIs
| Measure | Weight | Sonar | Claude Haiku 3 | Qwen Plus Character (Japanese) |
|---|---|---|---|---|
| Price | 50% | 50 | 64 | 57 |
| Inputs & features | 30% | 0 | 60 | 25 |
| Context window | 20% | 24 | 32 | 0 |
| Overall | 100% | 30/100 | 56/100 | 36/100 |
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 | SonarPerplexity | Claude Haiku 3Anthropic | Qwen Plus Character (Japanese)Alibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | 118.4 | — |
| ECI rank | — | #143 of 148 | — |
| GPQA DiamondGraduate-level science questions | — | 36.3% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 1.8% | — |
| Price per million tokens | |||
| Input | $1.00 | $0.25 (best) | $0.50 |
| Output | $1.00 (best) | $1.25 | $1.40 |
| Cached input | — | — | — |
| Blended (3:1) | $1.00 | $0.50 (best) | $0.725 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Perplexity API | Median of 2 providers | Official Alibaba API |
| Limits | |||
| Context window | 128,000 tokens | 200,000 tokens (best) | 8,192 tokens |
| Max output | 4,096 tokens (best) | 4,096 tokens (best) | 512 tokens |
| 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 | Proprietary | Proprietary | Proprietary |
| API model ID | sonar | — | qwen-plus-character-ja |
| API providers | 6 (best) | 2 | 1 |
| Released | Jan 1, 2024 | Mar 13, 2024 | Jan 2024 |
| Knowledge cutoff | Sep 1, 2025 | Aug 31, 2023 | Apr 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Sonar$12.00
- Claude Haiku 3$5.00
- Qwen Plus Character (Japanese)$7.80
Which should you choose?
Which is better: Sonar, Claude Haiku 3 or Qwen Plus Character (Japanese)?
Claude Haiku 3 is the better all-round choice, scoring 56/100 against Qwen Plus Character (Japanese) (36) and Sonar (30). It leads on price, inputs & features and context window. 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, Sonar, Claude Haiku 3 or Qwen Plus Character (Japanese)?
Claude Haiku 3 is cheaper at $0.25 input / $1.25 output per million tokens (median across 2 API providers). Qwen Plus Character (Japanese) costs $0.50 input / $1.40 output per million tokens (official Alibaba API price); Sonar costs $1.00 input / $1.00 output per million tokens (official Perplexity API price). At a typical mix of three input tokens to one output token, that is $0.50 per million tokens for Claude Haiku 3 versus $0.725 for Qwen Plus Character (Japanese) (1.4× as much) and $1.00 for Sonar (2× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Sonar has not been scored yet, Claude Haiku 3 has an ECI of 118.4 and Qwen Plus Character (Japanese) has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Sonar, Claude Haiku 3 and Qwen Plus Character (Japanese) yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Sonar 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 Sonar and 8,192 for Qwen Plus Character (Japanese). Maximum output per response: Sonar up to 4,096, Claude Haiku 3 up to 4,096, Qwen Plus Character (Japanese) up to 512 tokens.
Which can read images, PDFs, audio or video?
Sonar accepts text; Claude Haiku 3 accepts text, images and PDFs; Qwen Plus Character (Japanese) accepts text. Claude Haiku 3 handles the widest range of inputs.
Are any of these open source?
No. Sonar, Claude Haiku 3 and Qwen Plus Character (Japanese) are proprietary and only available through APIs and apps.
Which is newer?
Claude Haiku 3 is the newest, released Mar 13, 2024. Sonar came out Jan 1, 2024; Qwen Plus Character (Japanese) came out Jan 2024. Knowledge cutoff: Sonar Sep 1, 2025, Claude Haiku 3 Aug 31, 2023, Qwen Plus Character (Japanese) Apr 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.
