Updated November 7, 2026. Rank says Inkling 2 Small is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
Inkling 2 Small has the higher public point estimate, 59.06 versus 43.94. Their conditional score ranges overlap. These ranges do not establish rank confidence. 10 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Thinking Machines Lab
59.06/100
Estimated · Public rank #56
Conditional range 44.7–73.4
Reflection AI
43.94/100
Estimated · Public rank #124
Conditional range 34.2–53.7
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
Tool use, computer use, and multi-step task completion
Inkling 2 Small
Inkling 2 Small has the higher public agentic point estimate, 59.9 to 44.8, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Beam 1.0 501B-A23B is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.
The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.
Directional only · BenchAlign v5.8
Inkling 2 Small has the higher coding point estimate. Conditional score ranges do not establish rank confidence.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
2 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.
BrowseCompAgentic
Normalized gap 13.4LongBench v2Reasoning
Normalized gap 3.1SWE MultilingualCoding
Normalized gap 2.9SWE-bench VerifiedCoding
Normalized gap 0.6Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.
| Category | Inkling 2 Small | Beam 1.0 501B-A23B | Basis | Reading |
|---|---|---|---|---|
| Agentic | 59.9Supported · #26/131 | 44.8Supported · #60/131 | Like-for-likeBenchAlign v5.8 lane · 5 vs 6 public rows | Inkling 2 Small leads · intervals overlap |
| Coding | 59.7Supported · #20/157 | 30.5Estimated · #104/157 | Directional onlyBenchAlign v5.8 lane · 6 vs 7 public rows | Directional only |
| Knowledge | 60.4Estimated · #46/178 | 49.2Supported · #84/178 | Directional onlyBenchAlign v5.8 lane · 2 vs 2 public rows | Directional only |
| Reasoning | 86.1Unranked · 2 rankable rows | 77.0Unranked · 2 rankable rows | Not comparableProvisional lane · 1 vs 1 weighted rows | Not comparable |
| Multimodal | 86.6#12/59 | Not ranked | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Math | 85.9Unranked · 2 rankable rows | Not ranked | Not comparableProvisional lane · 1 vs 1 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
1K fresh input + 500 output tokens
Beam 1.0 501B-A23B has no comparable published API token rate.
50K fresh input + 3K output tokens
Beam 1.0 501B-A23B has no comparable published API token rate.
200K cached + 20K fresh input + 10K output tokens
Beam 1.0 501B-A23B has no comparable published API token rate.
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
Maximum documented context; output-token limits may be lower.
Inkling 2 Small
Beam 1.0 501B-A23B
Inkling 2 Small
Not sourced
Beam 1.0 501B-A23B
Beam-1.0-501B-A23B
Reflection developer docs, ModelsA missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Inkling 2 Small
$0.03 per 1M cached input tokens
Tinker models and pricingBeam 1.0 501B-A23B
No comparable hosted API rate
Reflection launch postInkling 2 Small
Not sourced
Beam 1.0 501B-A23B
Inkling 2 Small
Not sourced
Beam 1.0 501B-A23B
Inkling 2 Small
Not sourced
Beam 1.0 501B-A23B
Open Weights · Hugging Face, self-hosted inference, Reflection API public beta, partner endpoints
Reflection Beam 1.0 BF16 model cardInkling 2 Small
Hybrid
Beam 1.0 501B-A23B
Reasoning
Inkling 2 Small
Proprietary
Beam 1.0 501B-A23B
Open Weight
Inkling 2 Small
Proprietary
Beam 1.0 501B-A23B
Open Weight
Inkling 2 Small
2026-11-05
Beam 1.0 501B-A23B
2026-10-16
Inkling 2 Small has the higher public point estimate, 59.06 versus 43.94. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.
Inkling 2 Small scores higher for coding on the public lane, 59.7 to 30.5. Beam 1.0 501B-A23B is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Inkling 2 Small has the higher public agentic tasks point estimate, 59.9 to 44.8, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Both models do not have comparable published API token rates, so this page does not name a universal price winner.
Both models list the same context window, 1M.
Estimates at 50,000 req/day · 1000 tokens/req average.
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Terminal-Bench 2.1
Inkling 2 Small leads this result
BrowseComp
Inkling 2 Small leads this result
DeepSearchQA
Inkling 2 Small leads this result
MCP Atlas
Inkling 2 Small leads this result
JobBench
Not directly comparable
τ³-bench results
Not directly comparable
HLE w/ tools
Not directly comparable
SWE-bench Verified
Inkling 2 Small leads this result
SWE Multilingual
Inkling 2 Small leads this result
sweMarathon
Not directly comparable
Terminal-Bench 2.1
Inkling 2 Small leads this result
DeepSWE
Inkling 2 Small leads this result
PostTrainBench v1.2
Not directly comparable
SWE-bench Pro
Not directly comparable
SWE-Atlas Codebase QnA
Not directly comparable
SciCode
Not directly comparable
CharXiv
Not directly comparable
CharXiv w/o tools
Not directly comparable
Chartography (no tools)
Not directly comparable
Chartography (tools)
Not directly comparable
BabyVision
Not directly comparable
BabyVision w/ Python
Not directly comparable
ScreenSpot Pro
Not directly comparable
PerceptionBench
Not directly comparable
MathVision
Not directly comparable
IFBench
Not directly comparable
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 6,100+ subscribers.
Last updated November 7, 2026