text model comparison
Inkling 2 Small vs MiniMax M3.1 Flash
Inkling 2 Small and MiniMax M3.1 Flash are both current text models, from Thinking Machines Lab and MiniMax. MiniMax M3.1 Flash is 50% cheaper per 1M input tokens than Inkling 2 Small, $0.15 vs $0.30. In Thinking Machines Lab's Inkling 2 Small model card, Inkling 2 Small scores 72.1% on DeepSWE v1.1 and MiniMax M3.1 Flash 73.7%. MiniMax M3.1 Flash has the larger context window, 1,000,000 vs 262,144 tokens.
- Lower price per 1M input tokens
- MiniMax M3.1 Flash$0.15 against $0.30
- Longer context window
- MiniMax M3.1 Flash1M 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
Inkling 2 Small and MiniMax M3.1 Flash, 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 | MiniMax M3.1 Flash |
|---|---|---|
| Price | ||
| Price per 1M input tokens | $0.30 | $0.15 (better) |
| Price per 1M output tokens | $1 | $0.60 (better) |
| Independent benchmarks | ||
| Arena WebDev | Not measured | 1582 Elo (#27 of 46) |
| Specs | ||
| Provider | Thinking Machines Lab | MiniMax |
| Release date | November 5, 2026 | October 19, 2026 |
| Access | API only | API and open weights |
| Context window | 262,144 tokens | 1,000,000 tokens |
| Max output | Not reported | Not reported |
| Input | text, image | text, image, video |
| Output | text | text |
No independent benchmark has scored both models yet. Each rank counts the current models scored on that benchmark.
Scores:Arena · 2026-11-03
Provider results
What the labs report
Results tables a lab published with one of its models, where it lists both Inkling 2 Small and MiniMax M3.1 Flash. 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 | MiniMax M3.1 Flash |
|---|---|---|
| DeepSWE v1.1 | 72.1% | 73.7% (better) |
| Vibe Code Bench v1.1 | 81.6% (better) | 73.9% |
| SWE-bench Multilingual | 81.2% (better) | 79.9% |
| SWE-bench Pro v2hard set | 86.3% (better) | 84.3% |
| SWE-bench Pro v2full set | 97.7% (better) | 96.6% |
| SWE-bench Verified | 82.2% (better) | 81.1% |
| MCP Atlaspublic set | 85.0% (better) | 80.4% |
| Finance Agent v2.1 | 67.5% (better) | 58.8% |
| Excel Modeling Benchmark v1.1 | 69.5% (better) | 67.8% |
| Tax Agent Bench | 65.8% (better) | 62.7% |
| APEX-Accounting v1.1pass@1 | 14.5% (better) | 13.5% |
| APEX-Accounting v1.1mean score | 62.0% (better) | 60.0% |
| Harvey LAB v1.1 | 21.7% (better) | 7.5% |
| Legal Research Bench | 46.6% (better) | 34.1% |
| BabyVisionwith Python | 93.7% (better) | 91.0% |
| CharXiv (RQ) | 85.6% (better) | 82.5% |
| Chartography | 36.7% (better) | 12.6% |
| SAGE v1.1 | 88.6% (better) | 85.3% |
| GPQA-Diamond | 93.0% (better) | 86.7% |
| LongBench v2 | 70.6% (better) | 60.9% |
| ComplexConstraints v1.0 | 44.5% (better) | 23.2% |
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 MiniMax M3.1 Flash land among the current models of their task, on every independent benchmark, on price and on context.
Where each stands
Only MiniMax M3.1 Flash has a current Arena WebDev score: #27 of 46. Each bar is the share of current models it beats.
Independent benchmarks
Arena WebDev
Inkling 2 Small: Not scored
MiniMax M3.1 Flash:#27of 46
1,582 Elo · ahead of 40%
Price and context
Price per 1M input tokens
Inkling 2 Small:#11of 58
$0.30 · cheaper than 75%
MiniMax M3.1 Flash:#5of 58
$0.15 · cheaper than 91%
Price per 1M output tokens
Inkling 2 Small:#10of 58
$1 · cheaper than 84%
MiniMax M3.1 Flash:#6of 58
$0.60 · cheaper than 91%
Context window
Inkling 2 Small:#57of 67
262K tokens · longer than 12%
MiniMax M3.1 Flash:#27of 67
1M tokens · longer than 24%
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 1.9 times as much as MiniMax M3.1 Flash, at each provider's listed rates.
10M input and 2M output tokens
Inkling 2 Small costs 1.9× as much
- Inkling 2 Small
- $5
- MiniMax M3.1 Flash
- $2.70
The same, with 9M of the input tokens cached
Inkling 2 Small costs 1.7× as much
- Inkling 2 Small
- $2.57
- MiniMax M3.1 Flash
- $1.49
| Workload or rate | Inkling 2 Small | MiniMax M3.1 Flash |
|---|---|---|
| Example workloads | ||
| 10M input and 2M output tokens | $5 | $2.70 (better) |
| The same, with 9M of the input tokens cached | $2.57 | $1.49 (better) |
| Other listed rates | ||
| 1M input tokens, cached | $0.03 | $0.015 (better) |
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
No measured lead over MiniMax M3.1 Flash 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
MiniMax M3.1 Flash
Where it leads
- Lower input and output prices, $0.15 and $0.60 vs $0.30 and $1 per 1M tokens
- Larger context window 1,000,000 vs 262,144 tokens
- Accepts video input
- Open weights you can run yourself
- Cheaper cached input, $0.015 vs $0.03 per 1M tokens
Best for
- Low-cost coding and agent loops
- Long-context multimodal work on a budget
Watch out for
- Thinking cannot be turned off; effort runs from low to max, and max is the default
- MiniMax gives two parameter counts (about 428B in the model card, 220B in the file metadata)
From benchmark to production
Building on Inkling 2 Small or MiniMax M3.1 Flash?
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 MiniMax M3.1 Flash FAQ
Which is cheaper, Inkling 2 Small or MiniMax M3.1 Flash?
MiniMax M3.1 Flash is 50% cheaper per 1M input tokens than Inkling 2 Small, $0.15 vs $0.30. For 10M input and 2M output tokens, Inkling 2 Small costs $5 and MiniMax M3.1 Flash $2.70 at standard rates.
Which is cheaper with prompt caching, Inkling 2 Small or MiniMax M3.1 Flash?
Inkling 2 Small charges $0.03 per 1M cached input tokens, 90% below its standard input rate, and MiniMax M3.1 Flash $0.015, 90% below. With 9M of 10M input tokens cached and 2M output tokens, Inkling 2 Small costs $2.57 and MiniMax M3.1 Flash $1.49.
How do Inkling 2 Small and MiniMax M3.1 Flash compare in Thinking Machines Lab's own results?
In the Inkling 2 Small model card (November 5, 2026), MiniMax M3.1 Flash leads on DeepSWE v1.1, 73.7% to 72.1%; Inkling 2 Small leads on Vibe Code Bench v1.1, 81.6% to 73.9%; Inkling 2 Small leads on SWE-bench Multilingual, 81.2% to 79.9%. These are Thinking Machines Lab's figures, not independent measurements.
Which has the larger context window, Inkling 2 Small or MiniMax M3.1 Flash?
MiniMax M3.1 Flash has the larger context window, 1,000,000 vs 262,144 tokens.
How do Inkling 2 Small and MiniMax M3.1 Flash differ in features?
Inkling 2 Small takes text and image input; MiniMax M3.1 Flash takes text, image and video.
Can I run Inkling 2 Small or MiniMax M3.1 Flash myself?
MiniMax M3.1 Flash 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 MiniMax M3.1 Flash
Related comparisons
- Claude Haiku 5.5 vs Inkling 2 Small
- Beam 1.0 vs MiniMax M3.1 Flash
- DeepSeek-V4.1-Flash vs Inkling 2 Small
- Claude Haiku 5.5 vs MiniMax M3.1 Flash
- Gemini 3.5 Flash-Lite vs Inkling 2 Small
- GLM-5.3-Flash vs MiniMax M3.1 Flash
- Gemini 3.8 Flash vs Inkling 2 Small
- GPT-6 Luna vs MiniMax M3.1 Flash
- GLM-5.3-Flash vs Inkling 2 Small
- MiMo-V2.6-Flash vs MiniMax M3.1 Flash
- GLM-5.3 vs Inkling 2 Small
- MiniMax M3.1 Flash vs Muse Spark Open
Production evaluation
Choosing between Inkling 2 Small and MiniMax M3.1 Flash?
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