Inkling-Small
Explore Inkling-Small’s published benchmark results and provider offerings below. More comparable task results are needed to describe its strongest areas.
Updated: Data as of:
Reported highlights
| Benchmark | Measures | Score |
|---|---|---|
| SWE-bench ↗Verified / published open-model reports | Coding | 80.2% (opens in a new tab) |
| Terminal-Bench ↗2.1 / published open-model reports | Working in a terminal | 64.7% (opens in a new tab) |
| BrowseComp ↗Published open-model reports | Web research | 77.4% (opens in a new tab) |
| Humanity's Last Exam ↗HLE — source does not specify subset | Expert reasoning | 47.8% (opens in a new tab) |
Model details
| Model | Inkling-Small |
|---|---|
| Agent Index v1.3 | Insufficient coverage (0/7) · Preview |
| Creator | Thinking Machines (opens in a new tab) |
| Availability | Open source / open weights |
| Context size | 1,000,000 tokens (opens in a new tab) |
| Max output | Not reported |
| Knowledge cutoff | Not reported |
| License | Apache 2.0 · Model weights ↗ (opens in a new tab) |
Pricing and performance
Per provider and reported configuration. Prices are USD per 1M tokens.
No provider pricing or performance reports have been added for this model yet.
Blended token cost
USD per 1M tokens · 50% input + 50% output · lower is better
No sourced current price for Inkling-Small.10 of 45 priced models selected
Pricing details and sources
Blended cost = (input price + output price) ÷ 2: 500,000 input and 500,000 output tokens. Each model uses its lowest sourced current provider rate, excluding batch and Flex tiers. Cache discounts, tool fees and workload-specific token usage are excluded. 52 models without complete sourced current prices are unavailable in this comparison. The default selection is this model and the nine closest in blended cost; if this model has no price, we show the ten cheapest. The scale stays fixed across pages of your selection.
| Model | Input / 1M | Output / 1M | Blended / 1M | Provider / source |
|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | $0.098 | $0.294 | $0.196 | DeepInfraDeepSeek V4.1 Flash 1017 (max) · Checked 2026-11-02 |
| DeepSeek V4.1 Flash | $0.14 | $0.42 | $0.28 | DeepInfraDeepSeek V4.1 Flash (max) · Checked 2026-11-02 |
| Claude Haiku 5.5 | $0.10 | $0.50 | $0.30 | Anthropic ↗Standard API, prompts up to 100K input tokens · Checked 2026-11-02 |
| GPT-6 Luna | $0.10 | $0.50 | $0.30 | OpenAI ↗Standard API, prompts up to 272K input tokens · Checked 2026-11-02 |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.325 | Z.aiGLM-5.3-Flash · Checked 2026-11-02 |
| MiniMax M3.1 Flash | $0.143 | $0.57 | $0.356 | GMIMiniMax-M3.1-Flash · Checked 2026-11-02 |
| GLM-5.3 | $0.20 | $0.64 | $0.42 | Multiverse ComputingGLM-5.3 (max) · Checked 2026-11-02 |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.653 | Xiaomi ↗Standard API, USD, uncached input · Checked 2026-11-02 |
| MiniMax M3 | $0.30 | $1.20 | $0.75 | MiniMaxMiniMax-M3 · Checked 2026-11-02 |
| DeepSeek V4 Pro 0813 | $0.50 | $2.00 | $1.25 | SystalyzeDeepSeek V4 Pro 0813 (max) · Checked 2026-11-02 |
Output speed
Output tokens per second · higher is better
No sourced output speed for Inkling-Small.10 of 33 models with reports selected
Measurement details and sources
Output speed measures generated tokens per second. Each model uses its fastest sourced current provider report. Batch and Flex tiers are excluded. Provider, configuration, prompt and reporting methods can differ, so these are reported observations rather than controlled head-to-head tests. 64 models have no qualifying sourced speed report. Defaults include this model and the nine closest reported values, or the ten leading models if this model has no report. The scale stays fixed across selected pages.
| Model | Output speed | Provider / configuration | Measurement | Source |
|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 1,075.275 t/s | Inco (FAST)DeepSeek V4.1 Flash 1017 (max) (FAST) | longmedianArtificial Analysis: DeepSeek V4.1 Flash 1017 (max) (FAST); host Inco (FAST); standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record. | SourceChecked 2026-11-02 |
| DeepSeek V4.1 Flash | 830.034 t/s | Baseten (FAST)DeepSeek V4.1 Flash (max) (FAST) | longmedianArtificial Analysis: DeepSeek V4.1 Flash (max) (FAST); host Baseten (FAST); standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record. | SourceChecked 2026-11-02 |
| MiniMax M3.1 Flash | 812.597 t/s | IncoMiniMax-M3.1-Flash | longmedianArtificial Analysis: MiniMax-M3.1-Flash; host Inco; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record. | SourceChecked 2026-11-02 |
| GLM-5.3 | 688.217 t/s | SystalyzeGLM-5.3 (max) | longmedianArtificial Analysis: GLM-5.3 (max); host Systalyze; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record. | SourceChecked 2026-11-02 |
| Kimi K3 | 481.694 t/s | Inco (FAST)Kimi K3 (max) (FAST) | longmedianArtificial Analysis: Kimi K3 (max) (FAST); host Inco (FAST); standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record. | SourceChecked 2026-11-02 |
| GPT-6.1 Sol | 342.946 t/s | OpenAI (Ultrafast)GPT-6.1 Sol (max) (Ultrafast) | longmedianArtificial Analysis: GPT-6.1 Sol (max) (Ultrafast); host OpenAI (Ultrafast); standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record. | SourceChecked 2026-11-02 |
| DeepSeek V4 Pro 0813 | 305.002 t/s | SystalyzeDeepSeek V4 Pro 0813 (max) | longmedianArtificial Analysis: DeepSeek V4 Pro 0813 (max); host Systalyze; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record. | SourceChecked 2026-11-02 |
| Muse Spark 1.1 | 294.835 t/s | MetaMuse Spark 1.1 (xhigh) | longmedianArtificial Analysis: Muse Spark 1.1 (xhigh); host Meta; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record. | SourceChecked 2026-11-02 |
| Muse Spark 1.2 | 277.574 t/s | MetaMuse Spark 1.2 (xhigh) | longmedianArtificial Analysis: Muse Spark 1.2 (xhigh); host Meta; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record. | SourceChecked 2026-11-02 |
| Muse Spark 1.3 | 195.207 t/s | MetaMuse Spark 1.3 (max) | longmedianArtificial Analysis: Muse Spark 1.3 (max); host Meta; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record. | SourceChecked 2026-11-02 |
Latency
Time to first token in seconds · lower is better
No sourced time-to-first-token latency for Inkling-Small.10 of 32 models with reports selected
Measurement details and sources
Latency measures time to first token (TTFT), converted to seconds. Each model uses its lowest sourced current TTFT report; total response time is excluded. Batch and Flex tiers are excluded. Provider, configuration, prompt and reporting methods can differ, so these are reported observations rather than controlled head-to-head tests. 65 models have no qualifying sourced latency report. Defaults include this model and the nine closest reported values, or the ten leading models if this model has no report. The scale stays fixed across selected pages.
| Model | Latency | Provider / configuration | Measurement | Source |
|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 0.182 s | Baseten (FAST)DeepSeek V4.1 Flash 1017 (max) (FAST) | longmedianArtificial Analysis: DeepSeek V4.1 Flash 1017 (max) (FAST); host Baseten (FAST); standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record. | SourceChecked 2026-11-02 |
| DeepSeek V4.1 Flash | 0.311 s | Together AIDeepSeek V4.1 Flash (max) | longmedianArtificial Analysis: DeepSeek V4.1 Flash (max); host Together AI; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record. | SourceChecked 2026-11-02 |
| MiniMax M3.1 Flash | 0.584 s | Together AIMiniMax-M3.1-Flash | longmedianArtificial Analysis: MiniMax-M3.1-Flash; host Together AI; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record. | SourceChecked 2026-11-02 |
| GLM-5.3 | 0.597 s | Together AIGLM-5.3 (max) | longmedianArtificial Analysis: GLM-5.3 (max); host Together AI; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record. | SourceChecked 2026-11-02 |
| MiniMax M3 | 0.699 s | MiniMaxMiniMax-M3 | source aggregatemedianExplicit first-party AA measurement; reasoning configuration retained. Cross-provider medians are excluded. Retrieval time is not measurement time. | SourceChecked 2026-11-02 |
| DeepSeek V4 Pro 0813 | 0.832 s | DigitalOceanDeepSeek V4 Pro 0813 (max) | longmedianArtificial Analysis: DeepSeek V4 Pro 0813 (max); host DigitalOcean; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record. | SourceChecked 2026-11-02 |
| Kimi K3 | 0.87 s | DatabricksKimi K3 (max) | longmedianArtificial Analysis: Kimi K3 (max); host Databricks; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record. | SourceChecked 2026-11-02 |
| Claude Opus 4.6 | 1.35 s | AmazonClaude Opus 4.6 (non-reasoning, high) | longmedianArtificial Analysis: Claude Opus 4.6 (non-reasoning, high); host Amazon; standard uncached input/output pricing. TTFT is the first streamed token, which may be reasoning. Retrieval time is not measurement time; region/concurrency/quantization not specified in this record. | SourceChecked 2026-11-02 |
| GLM-5.3-Flash | 1.546 s | Z.aiGLM-5.3-Flash | source aggregatemedianExplicit first-party AA measurement; reasoning configuration retained. Cross-provider medians are excluded. Retrieval time is not measurement time. | SourceChecked 2026-11-02 |
| GLM-5.2 | 1.777 s | Z.aiGLM-5.2 (Max) | source aggregatemedianExplicit first-party AA measurement; reasoning configuration retained. Cross-provider medians are excluded. Retrieval time is not measurement time. | SourceChecked 2026-11-02 |
Reported benchmarks
All published results in our dataset, with versions, evaluation settings, and sources.
| Benchmark | Score | Evaluation setup | Source |
|---|---|---|---|
| BrowseCompPublished open-model reportsAccuracy · Higher is better | 77.4% | With context management; effort=0.99; temperature=1.0. Do not equate with another publisher compaction or search setup. · Tools enabled | Thinking Machines Lab ↗ (opens in a new tab)provider reported · 2026-07-30 |
| GPQADiamond / Artificial AnalysisAccuracy · Higher is better | 89.5% | GPQA Diamond; effort=0.99; temperature=1.0. Official model article credits Artificial Analysis; no conversion to another protocol. | Thinking Machines Lab ↗ (opens in a new tab)provider reported · 2026-07-30 |
| Humanity's Last ExamHLE — source does not specify subsetAccuracy · Higher is better | 47.8% | HLE with tools; effort=0.99; temperature=1.0. Source does not establish full versus text-only subset for this row. · Tools enabled | Thinking Machines Lab ↗ (opens in a new tab)provider reported · 2026-07-30 |
| Humanity's Last ExamStable HLE — text-only subsetAccuracy · Higher is better | 31.6% | Text-only, no tools; effort=0.99; temperature=1.0. Source credits externally reported evaluation. · subset: text-only · No tools | Thinking Machines Lab ↗ (opens in a new tab)provider reported · 2026-07-30 |
| IFBench58 constraint typesAccuracy · Higher is better | 82.2% | IFBench; effort=0.99; temperature=1.0. Reported in official model article; retained as a distinct reported cohort. | Thinking Machines Lab ↗ (opens in a new tab)provider reported · 2026-07-30 |
| MCP-AtlasApril 2026 / public 500Task success · Higher is better | 79.6% | Public subset only (not the 79.2 all-set score); effort=0.99; temperature=1.0. Source credits Scale AI. · split: public | Thinking Machines Lab ↗ (opens in a new tab)provider reported · 2026-07-30 |
| SWE-benchVerified / published open-model reportsResolved · Higher is better | 80.2% | harness: Thinking Machines bash-only harness · Bash-only harness; effort=0.99; temperature=1.0; coding trajectory cap=256K tokens. Not mini-SWE-agent 2.0.0. | Thinking Machines Lab ↗ (opens in a new tab)provider reported · 2026-07-30 |
| Terminal-Bench2.1 / published open-model reportsTask success · Higher is better | 64.7% | harness: Thinking Machines internal coding harness · Internal coding harness, best harness; effort=0.99; temperature=1.0; 256K coding trajectory cap. Source says contaminated web-search solutions scored zero. | Thinking Machines Lab ↗ (opens in a new tab)provider reported · 2026-07-30 |