text model comparison
Claude Haiku 5.5 vs Inkling 2 Small
Claude Haiku 5.5 and Inkling 2 Small are both current text models, from Anthropic and Thinking Machines Lab. Claude Haiku 5.5 is 67% cheaper per 1M input tokens than Inkling 2 Small, $0.10 vs $0.30. In Thinking Machines Lab's Inkling 2 Small model card, Claude Haiku 5.5 scores 59.9% on DeepSWE v1.1 and Inkling 2 Small 72.1%. Claude Haiku 5.5 has the larger context window, 1,000,000 vs 262,144 tokens.
- Lower price per 1M input tokens
- Claude Haiku 5.5$0.10 against $0.30
- Longer context window
- Claude Haiku 5.51M tokens against 262K tokens
- Newer release
- Inkling 2 SmallNov 2026 against Oct 2026
Data verified November 6, 2026 · Dataset 2026-11-06
Side by side
Claude Haiku 5.5 and Inkling 2 Small, line by line
Prices in effect today, compared at the same tier wherever both list one. The better value in each row is highlighted.
| Fact | Claude Haiku 5.5 | Inkling 2 Small |
|---|---|---|
| Price | ||
| Price per 1M input tokens | $0.10 (better) | $0.30 |
| Price per 1M output tokens | $0.50 (better) | $1 |
| Independent benchmarks | ||
| Arena Text | 1425 Elo (#42 of 52) | Not measured |
| Arena WebDev | 1589 Elo (#25 of 46) | Not measured |
| GPQA Diamond | 89.6% (#30 of 41) | Not measured |
| FrontierMath Tiers 1-3 (v2) | 75.1% (#19 of 41) | Not measured |
| SimpleQA Verified | 23.8% (#35 of 38) | Not measured |
| Specs | ||
| Provider | Anthropic | Thinking Machines Lab |
| Release date | October 7, 2026 | November 5, 2026 |
| Access | API only | API only |
| Context window | 1,000,000 tokens | 262,144 tokens |
| Max output | 128,000 tokens | Not reported |
| Input | text, image | text, image |
| Output | text | text |
No independent benchmark has scored both models yet. Each rank counts the current models scored on that benchmark.
Provider results
What the labs report
Results tables a lab published with one of its models, where it lists both Claude Haiku 5.5 and Inkling 2 Small. These are the lab's own figures, not independent measurements, and each table is read on its own: labs run benchmarks with different harnesses and budgets.
Thinking Machines Lab, Inkling 2 Small model card, November 5, 2026Thinking Machines Lab · 2026-11-06
| Benchmark | Claude Haiku 5.5 | Inkling 2 Small |
|---|---|---|
| DeepSWE v1.1 | 59.9% | 72.1% (better) |
| Vibe Code Bench v1.1 | 90.4% (better) | 81.6% |
| SWE-Marathon v1.1 | 50.0% (better) | 38.8% |
| SWE-bench Multilingual | 83.7% (better) | 81.2% |
| SWE-bench Multimodal v2 | 44.0% (better) | 43.1% |
| SWE-bench Pro v2hard set | 52.9% | 86.3% (better) |
| SWE-bench Pro v2full set | 87.2% | 97.7% (better) |
| SWE-bench Verified | 88.9% (better) | 82.2% |
| BioMysteryBench | 70.4% (better) | 70.0% |
| MCP Atlaspublic set | 81.0% | 85.0% (better) |
| Finance Agent v2.1 | 65.4% | 67.5% (better) |
| Excel Modeling Benchmark v1.1 | 65.5% | 69.5% (better) |
| Tax Agent Bench | 62.2% | 65.8% (better) |
| APEX-Accounting v1.1pass@1 | 15.3% (better) | 14.5% |
| APEX-Accounting v1.1mean score | 62.2% (better) | 62.0% |
| Diligence Benchbest harness | 40.8% | 58.1% (better) |
| Harvey LAB v1.1 | 4.2% | 21.7% (better) |
| Legal Research Bench | 43.8% | 46.6% (better) |
| CharXiv (RQ) | 84.4% | 85.6% (better) |
| Chartography | 46.4% (better) | 36.7% |
| SAGE v1.1 | 89.8% (better) | 88.6% |
| GPQA-Diamond | 89.8% | 93.0% (better) |
| LongBench v2 | 65.3% | 70.6% (better) |
| ComplexConstraints v1.0 | 36.8% | 44.5% (better) |
| CyberBench v1.1 | 75.5% (better) | 72.7% |
Thinking Machines' table from the Inkling 2 Small model card, run at effort 0.99 (xhigh) with a 1M-token trajectory limit; where a benchmark's owner publishes scores (Datacurve, Scale AI, Surge, Mercor, Thoughtful, Vals), Thinking Machines uses them. DeepSeek-V4.1-Flash is the 1017 build. Left out here: the Artificial Analysis and Vals indexes, the rows Artificial Analysis ran (FrontierCode, Terminal-Bench, GDP.pdf, MMMU-Pro, HLE, CritPt, AA-LCR, AA-Omniscience, AutomationBench, EnterpriseOps-Gym, Tau 3 Banking), Arena and DesignArena ratings, PMPP-Hard (not a percentage), the safety rows, and JobBench, DAYJOB and Humanity's Sixth Sense, which we could not confirm are public.
Charts
Against every current text model
Where Claude Haiku 5.5 and Inkling 2 Small land among the current models of their task, on every independent benchmark, on price and on context.
Where each stands
Only Claude Haiku 5.5 has a current Arena Text score: #42 of 52. Each bar is the share of current models it beats.
Independent benchmarks
Arena Text
Claude Haiku 5.5:#42of 52
1,425 Elo · ahead of 18%
Inkling 2 Small: Not scored
Arena WebDev
Claude Haiku 5.5:#25of 46
1,589 Elo · ahead of 47%
Inkling 2 Small: Not scored
GPQA Diamond
Claude Haiku 5.5:#30of 41
89.6% · ahead of 28%
Inkling 2 Small: Not scored
FrontierMath Tiers 1-3 (v2)
Claude Haiku 5.5:#19of 41
75.1% · ahead of 55%
Inkling 2 Small: Not scored
SimpleQA Verified
Claude Haiku 5.5:#35of 38
23.8% · ahead of 8%
Inkling 2 Small: Not scored
Price and context
Price per 1M input tokens
Claude Haiku 5.5:#1of 58
$0.10 · cheaper than 96%
Inkling 2 Small:#11of 58
$0.30 · cheaper than 75%
Price per 1M output tokens
Claude Haiku 5.5:#3of 58
$0.50 · cheaper than 93%
Inkling 2 Small:#10of 58
$1 · cheaper than 84%
Context window
Claude Haiku 5.5:#27of 67
1M tokens · longer than 24%
Inkling 2 Small:#57of 67
262K tokens · longer than 12%
Quality against price
Claude Haiku 5.5 scores 1,425 at $0.2 (blended price per 1M tokens). The line joins the current models no other beats on both price and Arena Text score; hover any point to name it.
Quality against price: the data
| Model | Provider | Blended price per 1M tokens | Arena Text (Elo) |
|---|---|---|---|
| Gemini 4 Carbon | $4 | 1,528 | |
| Gemini 4 Argon | $4 | 1,520 | |
| Claude Opus 5.5 | Anthropic | $8 | 1,509 |
| Muse Wonder | Meta | $8 | 1,507 |
| Claude Fable 5 | Anthropic | $20 | 1,504 |
| Claude Fable 5.1 | Anthropic | $20 | 1,504 |
| Gemini 3.8 Flash | $1.50 | 1,496 | |
| Muse Spark 1.3 | Meta | $2 | 1,495 |
| Claude Opus 5 | Anthropic | $10 | 1,492 |
| Kimi K3 | Moonshot Kimi | $6 | 1,488 |
| GPT-5.6 Sol | OpenAI | $8 | 1,485 |
| Gemini 3.6 Flash | $3 | 1,483 | |
| GPT-5.5 | OpenAI | $11 | 1,482 |
| Claude Opus 4.8 | Anthropic | $10 | 1,482 |
| Qwen3.8-Max | Alibaba Qwen | $3 | 1,482 |
| GPT-6.1 Sol | OpenAI | $4 | 1,481 |
| GLM-5.3 | Z.ai | $2.15 | 1,481 |
| MiMo-V2.6-Pro | Xiaomi MiMo | $0.54 | 1,480 |
| Claude Sonnet 5.5 | Anthropic | $4 | 1,477 |
| GLM-5.3-Flash | Z.ai | $0.24 | 1,477 |
| GPT-6 Astra | OpenAI | $20 | 1,476 |
| DeepSeek-V4.1-Flash | DeepSeek | $0.52 | 1,476 |
| GPT-5.4 | OpenAI | $5.63 | 1,475 |
| Gemini 3 Flash Preview | $1.13 | 1,473 | |
| Grok 4.20 | xAI | $1.56 | 1,472 |
| GPT-5.6 Terra | OpenAI | $4.50 | 1,467 |
| Grok 4.5 | xAI | $3 | 1,465 |
| DeepSeek-V4-Pro | DeepSeek | $1.98 | 1,465 |
| Claude Sonnet 5 | Anthropic | $4 | 1,462 |
| GPT-6 Sol | OpenAI | $4 | 1,458 |
| Gemini 3.5 Flash-Lite | $0.85 | 1,456 | |
| Grok 4.6 | xAI | $3 | 1,455 |
| GPT-5.6 Luna | OpenAI | $0.45 | 1,453 |
| MiMo-V2.6-Flash | Xiaomi MiMo | $0.18 | 1,448 |
| Step 5 Preview | StepFun | $1.43 | 1,448 |
| Grok 4.3 | xAI | $1.56 | 1,442 |
| GPT-6 Luna | OpenAI | $0.20 | 1,441 |
| Grok 4.7 | xAI | $3 | 1,441 |
| Mistral Large 4 | Mistral AI | $1.05 | 1,432 |
| Claude Haiku 5.5 | Anthropic | $0.20 | 1,425 |
| GPT-4.1 | OpenAI | $3.50 | 1,415 |
| Solar Pro 4 | Upstage | $0.52 | 1,388 |
| GPT-4.1 mini | OpenAI | $0.70 | 1,383 |
| GPT-4.1 nano | OpenAI | $0.18 | 1,322 |
Cost
What each costs
Example workloads at each provider's listed rates, then every other rate either one lists. The cheaper figure in each row is highlighted.
The same work, priced
For 10M input and 2M output tokens, Inkling 2 Small costs 2.5 times as much as Claude Haiku 5.5, at each provider's listed rates.
10M input and 2M output tokens
Inkling 2 Small costs 2.5× as much
- Claude Haiku 5.5
- $2
- Inkling 2 Small
- $5
The same, with 9M of the input tokens cached
Inkling 2 Small costs 2.2× as much
- Claude Haiku 5.5
- $1.19
- Inkling 2 Small
- $2.57
| Workload or rate | Claude Haiku 5.5 | Inkling 2 Small |
|---|---|---|
| Example workloads | ||
| 10M input and 2M output tokens | $2 (better) | $5 |
| The same, with 9M of the input tokens cached | $1.19 (better) | $2.57 |
| The same, through the batch API | $1 | Not listed |
| Other listed rates | ||
| 1M input tokens, cached | $0.01 (better) | $0.03 |
| 1M input tokens, 5-minute cache write | $0.125 | Not listed |
| 1M input tokens, 1-hour cache write | $0.20 | Not listed |
| 1M input tokens, batch | $0.05 | Not listed |
| 1M output tokens, batch | $0.25 | Not listed |
| 1M input tokens, prompts over 100K tokens | $0.50 | Not listed |
| 1M output tokens, prompts over 100K tokens | $2.50 | Not listed |
Your own bill will differ. These figures use list prices and example workloads. The AI Model Cost Audit reviews your real usage, shortlists models that score as well for each task for less, and estimates the savings.
Launch price $100, regular price $150
Verdict
When to choose each
Claude Haiku 5.5
Where it leads
- Lower input and output prices, $0.10 and $0.50 vs $0.30 and $1 per 1M tokens
- Larger context window 1,000,000 vs 262,144 tokens
- Cheaper cached input, $0.01 vs $0.03 per 1M tokens
- Batch pricing, $0.05 input and $0.25 output per 1M tokens
Best for
- High-volume classification, extraction and routing under the 100,000-token line
- Cost-sensitive fan-out steps where a frontier model is overkill
Watch out for
- Priced by prompt length, and it is a cliff rather than a taper: a request whose prompt passes 100,000 tokens is billed at $0.50 input and $2.50 output for the whole request, five times the short rate
- Cache reads and cache writes both count toward that 100,000-token measurement, so a large cached prefix can tip a request into the higher band on its own
- It is the only current Claude model whose 1M window is not priced uniformly; every other 4.6-and-later model bills a 900k request at the same rate as a 9k one
Inkling 2 Small
Where it leads
No measured lead over Claude Haiku 5.5 in this data.
Best for
- Agentic coding and office, finance and legal work at a low per-token price
- Teams that want to post-train their own variant on Tinker
Watch out for
- Closed weights for now: Thinking Machines says it will publish the full weights under Apache 2.0 the week after launch, once external safety testing ends; until then Tinker is the only way to use it
- Tinker serves it with a 64K or 256K context, although the model card lists up to 1M tokens
- In its lab's own table DeepSeek-V4.1-Flash scores higher on DeepSWE v1.1 (77.0% against 72.1%) and Claude Haiku 5.5 on Vibe Code Bench (90.4% against 81.6%); Thinking Machines also says it is less tuned for chat, and no independent benchmark score is recorded here yet
From benchmark to production
Building on Claude Haiku 5.5 or Inkling 2 Small?
Public scores rarely hold on your own data. We test both models on your real tasks, then build the agent or pipeline around the one that wins.
AI Model Cost AuditLaunch price $100, regular price $150What the audit includes
FAQ
Claude Haiku 5.5 vs Inkling 2 Small FAQ
Which is cheaper, Claude Haiku 5.5 or Inkling 2 Small?
Claude Haiku 5.5 is 67% cheaper per 1M input tokens than Inkling 2 Small, $0.10 vs $0.30. For 10M input and 2M output tokens, Claude Haiku 5.5 costs $2 and Inkling 2 Small $5 at standard rates.
Which is cheaper with prompt caching, Claude Haiku 5.5 or Inkling 2 Small?
Claude Haiku 5.5 charges $0.01 per 1M cached input tokens, 90% below its standard input rate, and Inkling 2 Small $0.03, 90% below. With 9M of 10M input tokens cached and 2M output tokens, Claude Haiku 5.5 costs $1.19 and Inkling 2 Small $2.57.
How do Claude Haiku 5.5 and Inkling 2 Small compare in Thinking Machines Lab's own results?
In the Inkling 2 Small model card (November 5, 2026), Inkling 2 Small leads on DeepSWE v1.1, 72.1% to 59.9%; Claude Haiku 5.5 leads on Vibe Code Bench v1.1, 90.4% to 81.6%; Claude Haiku 5.5 leads on SWE-Marathon v1.1, 50.0% to 38.8%. These are Thinking Machines Lab's figures, not independent measurements.
Which has the larger context window, Claude Haiku 5.5 or Inkling 2 Small?
Claude Haiku 5.5 has the larger context window, 1,000,000 vs 262,144 tokens.
Further reading
More on Claude Haiku 5.5 and Inkling 2 Small
Articles on Claude Haiku 5.5 and Inkling 2 Small
- Claude Haiku 5.5 vs Haiku 4.5: What Changes When You UpgradeOctober 14, 2026
- Claude Haiku 5.5: Real Cost, Benchmarks and When to Use ItOctober 14, 2026
Related comparisons
- Claude Fable 5 vs Claude Haiku 5.5
- DeepSeek-V4.1-Flash vs Inkling 2 Small
- Claude Haiku 5.5 vs Claude Opus 4.8
- Gemini 3.5 Flash-Lite vs Inkling 2 Small
- Claude Haiku 5.5 vs Claude Opus 5.5
- Gemini 3.8 Flash vs Inkling 2 Small
- Claude Haiku 5.5 vs Claude Sonnet 5
- GLM-5.3-Flash vs Inkling 2 Small
- Claude Haiku 5.5 vs Claude Sonnet 5.5
- GLM-5.3 vs Inkling 2 Small
- Claude Haiku 5.5 vs DeepSeek-V4.1-Flash
- GPT-6 Luna vs Inkling 2 Small
Production evaluation
Choosing between Claude Haiku 5.5 and Inkling 2 Small?
Public benchmarks narrow the shortlist. We run both on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- A head-to-head evaluation on your real workload
- Routing between models by cost and difficulty