text model comparison
Inkling 2 Small vs Kimi K3
Inkling 2 Small and Kimi K3 are both current text models, from Thinking Machines Lab and Moonshot Kimi. Inkling 2 Small is 90% cheaper per 1M input tokens than Kimi K3, $0.30 vs $3. In Thinking Machines Lab's Inkling 2 Small model card, Inkling 2 Small scores 72.1% on DeepSWE v1.1 and Kimi K3 68.5%. Kimi K3 has the larger context window, 1,048,576 vs 262,144 tokens.
- Lower price per 1M input tokens
- Inkling 2 Small$0.30 against $3
- Longer context window
- Kimi K31.05M tokens against 262K tokens
- Newer release
- Inkling 2 SmallNov 2026 against Jul 2026
Data verified November 6, 2026 · Dataset 2026-11-06
Side by side
Inkling 2 Small and Kimi K3, 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 | Inkling 2 Small | Kimi K3 |
|---|---|---|
| Price | ||
| Price per 1M input tokens | $0.30 (better) | $3 |
| Price per 1M output tokens | $1 (better) | $15 |
| Independent benchmarks | ||
| Arena Text | Not measured | 1488 Elo (#10 of 52) |
| Arena WebDev | Not measured | 1656 Elo (#14 of 46) |
| GPQA Diamond | Not measured | 93.1% (#17 of 41) |
| FrontierMath Tiers 1-3 (v2) | Not measured | 72.2% (#22 of 41) |
| SimpleQA Verified | Not measured | 50.6% (#20 of 38) |
| Specs | ||
| Provider | Thinking Machines Lab | Moonshot Kimi |
| Release date | November 5, 2026 | July 16, 2026 |
| Access | API only | API and open weights |
| Context window | 262,144 tokens | 1,048,576 tokens |
| Max output | Not reported | 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 Inkling 2 Small and Kimi K3. 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 | Inkling 2 Small | Kimi K3 |
|---|---|---|
| DeepSWE v1.1 | 72.1% (better) | 68.5% |
| Vibe Code Bench v1.1 | 81.6% | 85.0% (better) |
| Sudo L7 | 14.1% (better) | 13.9% |
| SWE-Marathon v1.1 | 38.8% | 48.1% (better) |
| SWE-bench Multilingual | 81.2% | 91.4% (better) |
| SWE-bench Multimodal v2 | 43.1% | 44.2% (better) |
| SWE-bench Pro v2hard set | 86.3% | 88.2% (better) |
| SWE-bench Pro v2full set | 97.7% | 97.7% |
| SWE-bench Verified | 82.2% | 93.4% (better) |
| PostTrainBench v1.2 | 31.9% (better) | 31.5% |
| BioMysteryBench | 70.0% | 72.6% (better) |
| DeepSearchQA | 90.9% | 95.0% (better) |
| MCP Atlasfull set | 85.4% (better) | 82.3% |
| MCP Atlaspublic set | 85.0% (better) | 84.2% |
| EnterpriseBench-CoreCraft | 71.8% (better) | 43.1% |
| Finance Agent v2.1 | 67.5% (better) | 60.0% |
| Excel Modeling Benchmark v1.1 | 69.5% | 71.3% (better) |
| Tax Agent Bench | 65.8% | 68.7% (better) |
| APEX-Accounting v1.1pass@1 | 14.5% (better) | 9.5% |
| APEX-Accounting v1.1mean score | 62.0% (better) | 56.7% |
| Harvey LAB v1.1 | 21.7% (better) | 12.9% |
| Legal Research Bench | 46.6% (better) | 46.2% |
| PerceptionBench | 64.7% (better) | 58.5% |
| ScreenSpot-Pro | 83.8% (better) | 73.8% |
| ScreenSpot-Prowith Python | 91.5% (better) | 83.2% |
| BabyVision | 68.6% (better) | 53.4% |
| BabyVisionwith Python | 93.7% (better) | 85.7% |
| CharXiv (RQ) | 85.6% (better) | 84.8% |
| CharXiv (RQ)with Python | 87.7% | 91.3% (better) |
| Chartography | 36.7% (better) | 26.6% |
| Chartographywith Python | 80.4% (better) | 68.1% |
| MathVision | 92.8% | 93.1% (better) |
| SAGE v1.1 | 88.6% (better) | 86.8% |
| GPQA-Diamond | 93.0% | 93.5% (better) |
| Apex 2025 | 63.5% | 65.6% (better) |
| HMMT Feb 2026 | 95.8% | 97.0% (better) |
| LongBench v2 | 70.6% (better) | 69.0% |
| ComplexConstraints v1.0 | 44.5% (better) | 37.9% |
| CyberBench v1.1 | 72.7% | 75.2% (better) |
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 Inkling 2 Small and Kimi K3 land among the current models of their task, on every independent benchmark, on price and on context.
Where each stands
Only Kimi K3 has a current Arena Text score: #10 of 52. Each bar is the share of current models it beats.
Independent benchmarks
Arena Text
Inkling 2 Small: Not scored
Kimi K3:#10of 52
1,488 Elo · ahead of 82%
Arena WebDev
Inkling 2 Small: Not scored
Kimi K3:#14of 46
1,656 Elo · ahead of 69%
GPQA Diamond
Inkling 2 Small: Not scored
Kimi K3:#17of 41
93.1% · ahead of 60%
FrontierMath Tiers 1-3 (v2)
Inkling 2 Small: Not scored
Kimi K3:#22of 41
72.2% · ahead of 48%
SimpleQA Verified
Inkling 2 Small: Not scored
Kimi K3:#20of 38
50.6% · ahead of 49%
Price and context
Price per 1M input tokens
Inkling 2 Small:#11of 58
$0.30 · cheaper than 75%
Kimi K3:#45of 58
$3 · cheaper than 23%
Price per 1M output tokens
Inkling 2 Small:#10of 58
$1 · cheaper than 84%
Kimi K3:#44of 58
$15 · cheaper than 23%
Context window
Inkling 2 Small:#57of 67
262K tokens · longer than 12%
Kimi K3:#12of 67
1.05M tokens · longer than 67%
Quality against price
Kimi K3 scores 1,488 at $6 (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, Kimi K3 costs 12 times as much as Inkling 2 Small, at each provider's listed rates.
10M input and 2M output tokens
Kimi K3 costs 12× as much
- Inkling 2 Small
- $5
- Kimi K3
- $60
The same, with 9M of the input tokens cached
Kimi K3 costs 14× as much
- Inkling 2 Small
- $2.57
- Kimi K3
- $35.70
| Workload or rate | Inkling 2 Small | Kimi K3 |
|---|---|---|
| Example workloads | ||
| 10M input and 2M output tokens | $5 (better) | $60 |
| The same, with 9M of the input tokens cached | $2.57 (better) | $35.70 |
| Other listed rates | ||
| 1M input tokens, cached | $0.03 (better) | $0.30 |
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
Inkling 2 Small
Where it leads
- Lower input and output prices, $0.30 and $1 vs $3 and $15 per 1M tokens
- Cheaper cached input, $0.03 vs $0.30 per 1M tokens
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
Kimi K3
Where it leads
- Larger context window 1,048,576 vs 262,144 tokens
- Open weights you can run yourself
Best for
- Teams that want a frontier-scale model they can also self-host, with one architecture across both paths
- Long-context work at mid-tier hosted pricing
Watch out for
- Hosted rates match Claude Sonnet 5 exactly at $3 / $15 while offering a larger context window, so the comparison turns on capability rather than price
- Running the open weights shifts cost to infrastructure, which the token rates recorded here do not represent
- Moonshot’s self-reported results place it ahead of Claude Opus 4.8 and GPT-5.5 but behind Claude Fable 5 and GPT-5.6 Sol; none of this was reproduced independently here
From benchmark to production
Building on Inkling 2 Small or Kimi K3?
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
Inkling 2 Small vs Kimi K3 FAQ
Which is cheaper, Inkling 2 Small or Kimi K3?
Inkling 2 Small is 90% cheaper per 1M input tokens than Kimi K3, $0.30 vs $3. For 10M input and 2M output tokens, Inkling 2 Small costs $5 and Kimi K3 $60 at standard rates.
Which is cheaper with prompt caching, Inkling 2 Small or Kimi K3?
Inkling 2 Small charges $0.03 per 1M cached input tokens, 90% below its standard input rate, and Kimi K3 $0.30, 90% below. With 9M of 10M input tokens cached and 2M output tokens, Inkling 2 Small costs $2.57 and Kimi K3 $35.70.
How do Inkling 2 Small and Kimi K3 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 68.5%; Kimi K3 leads on Vibe Code Bench v1.1, 85.0% to 81.6%; Inkling 2 Small leads on Sudo L7, 14.1% to 13.9%. These are Thinking Machines Lab's figures, not independent measurements.
Which has the larger context window, Inkling 2 Small or Kimi K3?
Kimi K3 has the larger context window, 1,048,576 vs 262,144 tokens.
Can I run Inkling 2 Small or Kimi K3 myself?
Kimi K3 is released as open weights you can run yourself; Inkling 2 Small is available through its provider's API only.
Further reading
More on Inkling 2 Small and Kimi K3
Articles on Inkling 2 Small and Kimi K3
- Qwen vs DeepSeek vs Kimi for Agents and CodingAugust 6, 2026
- Kimi K3 vs Opus 5 vs GPT-5.6 Sol: which model should you use?July 31, 2026
Related comparisons
- Claude Haiku 5.5 vs Inkling 2 Small
- Claude Opus 5.5 vs Kimi K3
- DeepSeek-V4.1-Flash vs Inkling 2 Small
- GPT-6 Luna vs Kimi K3
- Gemini 3.5 Flash-Lite vs Inkling 2 Small
- DeepSeek-V4.1-Flash vs Kimi K3
- Gemini 3.8 Flash vs Inkling 2 Small
- GPT-6 Astra vs Kimi K3
- GLM-5.3-Flash vs Inkling 2 Small
- Gemini 3.8 Flash vs Kimi K3
- GLM-5.3 vs Inkling 2 Small
- GLM-5.3 vs Kimi K3
Production evaluation
Choosing between Inkling 2 Small and Kimi K3?
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