Inkling Small vs Claude Haiku 5.5 vs Qwen3.8 27B
Claude Haiku 5.5 comes out ahead, 82 to 69 and 67 on our weighted score, and it is the cheaper option too.
Price in rating: Included · Exclude price
Thinking Machines
Inkling Small
69/100- ECI150.8
- Price$0.58 / $1.44
- Context1.05M
- Our pick
Anthropic
Claude Haiku 5.5
82/100- ECI160.3
- Price$0.10 / $0.50
- Context1M
Alibaba (Qwen)
Qwen3.8 27B
67/100- ECI152.7
- Price$0.40 / $2.42
- Context262K
Claude Haiku 5.5 is our pick
Claude Haiku 5.5 is the better all-round choice, scoring 82/100 against Inkling Small (69) and Qwen3.8 27B (67). It leads on capability, price and inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityClaude Haiku 5.5Capabilities Index (ECI): Claude Haiku 5.5 160.3 · Qwen3.8 27B 152.7 · Inkling Small 150.8
- Lowest priceClaude Haiku 5.5Claude Haiku 5.5 $0.20 · Inkling Small $0.795 · Qwen3.8 27B $0.905 per 1M tokens (3:1 blend)
- Longest contextInkling SmallInkling Small 1,048,576 · Claude Haiku 5.5 1,000,000 · Qwen3.8 27B 262,144 tokens
- Widest inputsSame inputsInkling Small: Text, Images, Audio · Claude Haiku 5.5: Text, Images, PDFs · Qwen3.8 27B: Text, Images, Video
- Self-hostingInkling Small and Qwen3.8 27BPublishes downloadable weights (Apache-2.0)
| Measure | Weight | Inkling Small | Claude Haiku 5.5 | Qwen3.8 27B |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 78 | 87 | 80 |
| Price | 25% | 52 | 79 | 50 |
| Inputs & features | 15% | 70 | 80 | 70 |
| Context window | 10% | 65 | 64 | 43 |
| Overall | 100% | 69/100 | 82/100 | 67/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 150.8 | 160.3 (best) | 152.7 |
| ECI rank | #65 of 158 | #20 of 158 (best) | #57 of 158 |
| GPQA DiamondGraduate-level science questions | 88.5% | 89.7% (best) | — |
| FrontierMath Tiers 1–3Research-level mathematics | 46.3% | 75.1% (best) | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 90.0% | 98.9% (best) | — |
| SimpleQA VerifiedShort factual questions | 19.1% | 23.8% (best) | — |
| Price per million tokens | |||
| Input | $0.58 | $0.10 (best) | $0.40 |
| Output | $1.44 | $0.50 (best) | $2.42 |
| Cached input | $0.116 | $0.01 (best) | — |
| Blended (3:1) | $0.795 | $0.20 (best) | $0.905 |
| Long-context rate | Same rate | Over 100K: $0.50 / $2.50 | Same rate |
| Price source | Official Thinking Machines API | Official Anthropic API | Median of 67 providers |
| Limits | |||
| Context window | 1,048,576 tokens (best) | 1,000,000 tokens | 262,144 tokens |
| Max output | 1,048,576 tokens (best) | 128,000 tokens | 32,768 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | Yes | No |
| Audio | Yes | No | No |
| Video | No | No | Yes |
| Reasoning | Yeslow · medium · high · xhigh · max | Yeslow · medium · high · xhigh · max | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | OpenApache-2.0 | Proprietary | Open |
| API model ID | thinkingmachines/Inkling-Small:peft:262144 | claude-haiku-5-5 | — |
| API providers | 12 | 48 | 72 (best) |
| Released | Jul 30, 2026 | Oct 7, 2026 | Aug 14, 2026 |
| Knowledge cutoff | — | Jun 2026 | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Inkling Small$8.68
Claude Haiku 5.5$2.00
Qwen3.8 27B$8.84
Which should you choose?
Which is better: Inkling Small, Claude Haiku 5.5 or Qwen3.8 27B?
Claude Haiku 5.5 is the better all-round choice, scoring 82/100 against Inkling Small (69) and Qwen3.8 27B (67). It leads on capability, price and inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, Inkling Small, Claude Haiku 5.5 or Qwen3.8 27B?
Claude Haiku 5.5 is cheaper at $0.10 input / $0.50 output per million tokens (official Anthropic API price). Inkling Small costs $0.58 input / $1.44 output per million tokens (official Thinking Machines API price); Qwen3.8 27B costs $0.40 input / $2.42 output per million tokens (median across 67 API providers). At a typical mix of three input tokens to one output token, that is $0.20 per million tokens for Claude Haiku 5.5 versus $0.795 for Inkling Small (4× as much) and $0.905 for Qwen3.8 27B (4.5× as much).
Which scores higher on benchmarks?
Claude Haiku 5.5 scores higher on the Capabilities Index (ECI): Claude Haiku 5.5 160.3 (#20 of 158), Qwen3.8 27B 152.7 (#57 of 158) and Inkling Small 150.8 (#65 of 158). Their confidence ranges do not overlap (158.1–162.7 vs 150.7–154.8), so the gap is a real one.
Which is better for coding?
There are no published SWE-bench Verified results for Inkling Small, Claude Haiku 5.5 and Qwen3.8 27B yet, so there is no like-for-like coding score. On overall capability, Claude Haiku 5.5 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?
Inkling Small has the largest context window at 1,048,576 tokens, against 1,000,000 for Claude Haiku 5.5 and 262,144 for Qwen3.8 27B. Maximum output per response: Inkling Small up to 1,048,576, Claude Haiku 5.5 up to 128,000, Qwen3.8 27B up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Inkling Small accepts text, images and audio; Claude Haiku 5.5 accepts text, images and PDFs; Qwen3.8 27B accepts text, images and video. They handle the same number of input types.
Are any of these open source?
Inkling Small and Qwen3.8 27B publishes its weights (Apache-2.0) and can be self-hosted; Claude Haiku 5.5 is proprietary.
Which is newer?
Claude Haiku 5.5 is the newest, released Oct 7, 2026. Qwen3.8 27B came out Aug 14, 2026; Inkling Small came out Jul 30, 2026. Knowledge cutoff: Claude Haiku 5.5 Jun 2026.
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.