BenchLeader

Agnes 2.5 Pro Theta vs Inkling

Full profiles: Agnes 2.5 Pro Theta (Sapiens AI) and Inkling (Thinking Machines): every benchmark, price and rank.

Updated · Data from 11 sources

As of 21 Nov 2026, Agnes 2.5 Pro Theta and Inkling are neck and neck on quality (50.7 vs 50.2 on the BenchLeader Index, inside the ±10.5 margin), and Agnes 2.5 Pro Theta is 17× cheaper at $0.150 vs $2.57 per 1M tokens blended. Inkling leads in every category we measure both in. Agnes 2.5 Pro Theta streams ~1.5× faster.

Key facts (as of 21 Nov 2026)

  • Agnes 2.5 Pro Theta scores 50.7 on the BenchLeader Index and Inkling scores 50.2 (BenchLeader, 21 Nov 2026).
  • Agnes 2.5 Pro Theta costs $0.150 per 1M tokens blended (list price, 21 Nov 2026).
  • Inkling costs $2.57 per 1M tokens blended (list price, 21 Nov 2026).
  • Agnes 2.5 Pro Theta streams ~1.5× faster than Inkling (Artificial Analysis, 7-day median, 21 Nov 2026).

Which to pick for…

The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.

Use casePickWhyConfidence
CodingEither45 vs 46 category scoreEither
ReasoningInkling52 vs 43 category scoreHigh
KnowledgeInkling60 vs 40 category scoreHigh
Chat quality (human preference)–Only Inkling has an Arena rating (59 category score)Not comparable
Lowest costAgnes 2.5 Pro Theta$0.150 vs $1.76 per 1M blended; agentic coding session $0.007 vs $0.076–
Fastest first answerInkling0.2 s (Inkling) vs 8.8 s (Agnes 2.5 Pro Theta) to the first answer token–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • Agnes 2.5 Pro Theta and Inkling are neck and neck on quality (50.7 vs 50.2, within the ±10.5 margin).
  • Inkling is stronger in coding, knowledge, reasoning.
  • Agnes 2.5 Pro Theta is 17× cheaper ($0.150 vs $2.57 per 1M blended).
  • Agnes 2.5 Pro Theta streams 1.7× faster (189 vs 110 tokens per second).

At a glance

SpecAgnes 2.5 Pro ThetaInkling
DeveloperSapiens AIThinking Machines
Released7 Nov 202615 Jul 2026
Context window (tokens)1,000,00065,536
Compared atAgnes 2.5 Pro ThetaInkling
Open weightsNoYes
Price in / out / cached input per 1M$0.100 / $0.300 / $0.010$1.00 / $4.05 / $0.170

Category by category

Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.

CategoryAgnes 2.5 Pro ThetaInklingLeader
Reasoning43.251.5Inkling
Coding45.346.2level
Agents & tools–30.2not comparable
Maths–54.1not comparable
Knowledge39.560.3Inkling
Human preference–58.8not comparable
Multimodal60.4–not comparable
Long context67.1–not comparable

On one chart

Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.

2550 avg75ReasoningCodingKnowledgeAgnes 2.5 Pro Theta, Reasoning: 43.2Agnes 2.5 Pro Theta, Coding: 45.3Agnes 2.5 Pro Theta, Knowledge: 39.5Inkling, Reasoning: 51.5Inkling, Coding: 46.2Inkling, Knowledge: 60.3

Not drawn, measured for fewer than two of these models: Agents & tools, Maths, Instruction following, Long context, Multimodal, Human preference.

Model, click to add or removeIndex

Where sources disagree

Across the 0 benchmarks both have, Agnes 2.5 Pro Theta leads 0, Inkling leads 0. Every overall index that rates both puts Agnes 2.5 Pro Theta ahead.

Overall indexAgnes 2.5 Pro ThetaInklingLeader
BenchLeader Index50.750.2neck and neck
AA Intelligence Index v5.0.124.011.0†Agnes 2.5 Pro Theta

Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).

Price, speed and latency

List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.

MeasureAgnes 2.5 Pro ThetaInkling
Blended price per 1M tokens$0.150$1.76
Input / output per 1M$0.100 / $0.300$1.00 / $4.05
Cached input per 1M$0.010$0.170
Price per task: chat reply$0.0001$0.0016
Price per task: summarize a 30-page report$0.0014$0.014
Price per task: code edit$0.0011$0.012
Price per task: agentic coding session$0.0072$0.076
Price per task: structured extraction$0.0003$0.0028
Agentic coding session, input mostly cached$0.0032$0.039
Cost per benchmark task (AA Index)$0.575–
Output tokens per task (AA Index)278k–
Of which reasoning229k–
Time per task (AA Index)24 min–
Output speed189 tok/s110 tok/s
Time to first answer8.8 s0.2 s
Time to a complete answer, last measured 13 Nov 202616.9 s–

Each model is compared at its best-ranked reasoning-effort setting. Agnes 2.5 Pro Theta scores 50.7 and takes 9 s to its first answer token. Inkling scores 50.2 and takes 0 s to its first answer token; Inkling (xhigh) scores 49.9 in 18 s, Inkling (high) scores 44.0 in 10 s. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.

Every benchmark

134 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.

MetricPublisherAgnes 2.5 Pro ThetaInkling
BenchLeader IndexBenchLeader50.750.2
Coding scoreBenchLeader45.346.2
Knowledge scoreBenchLeader39.560.3
Long context scoreBenchLeader67.1–
Multimodal scoreBenchLeader60.4–
Reasoning scoreBenchLeader43.251.5
Agents & tools scoreBenchLeader–30.2
Human preference scoreBenchLeader–58.8
Maths scoreBenchLeader–54.1
Blended price $/MBenchLeader$0.150$1.76
Output speedBenchLeader189 tok/s110 tok/s
Time to first answerBenchLeader8.8 s0.2 s
Context windowBenchLeader1,000,000 tokens65,536 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub–88.3%†
SimpleBenchSimpleBench–50.0%
Arena Hard PromptsArena (LMArena)–1463
LiveBench 2.0 ReasoningLiveBench–78.3%†
LiveBench 1.0 ReasoningLiveBench–78.3%†
GPQA Diamond (AA)Artificial Analysis–87.2%†
Humanity's Last Exam (AA)Artificial Analysis37.2%31.9%†
HLE-Diamond (AA)Artificial Analysis16.8%10.6%†
GPQA Diamond (Vals)Vals AI–87.1%
ARC-AGI-1ARC Prize–79.5%
ARC-AGI-2ARC Prize–36.5%
CritPtArtificial Analysis15.1%5.4%†
CritPt v2 hard subset (AA)Artificial Analysis26.0%18.0%†
HLE-Diamond (Scale)Scale AI SEAL–11.2%†
Arena ExpertArena (LMArena)–1474
Chess PuzzlesEpoch AI Benchmarking Hub–21.0%†
LMCAEpoch AI Benchmarking Hub–37.6%†
DTBenchEpoch AI Benchmarking Hub–87.5%†
Coding
SciCodeSciCode–47.0%†
WeirdMLWeirdML–32.3%†
FrontierCodeCognition–14.0%
Arena CodingArena (LMArena)–1494
Arena WebDevArena (LMArena)–1414
LiveBench 2.0 CodingLiveBench–48.7%†
LiveBench 1.0 CodingLiveBench–71.0%†
Show all 134 benchmarks
MetricPublisherAgnes 2.5 Pro ThetaInkling
Coding
SciCode (AA)Artificial Analysis56.0%47.0%†
LiveCodeBenchVals AI–85.5%
IOIVals AI–14.9%
SWE-bench (Vals)Vals AI–77.6%
Code MigrationVals AI–11.8%
Code Migration v1.1Vals AI–8.8%
ProgramBenchVals AI–0.0%
Vibe Code Bench 1-100Vals AI–7.3%
Vibe Code Bench v1.1Vals AI–19.2%
SWE-Bench Pro V2Scale AI SEAL–89.9%†
SWE-Bench Pro V2 HARDScale AI SEAL–56.9%†
ALE-BenchEpoch AI Benchmarking Hub–946
FrontierSWEEpoch AI Benchmarking Hub–4.1%†
WeirdML v3WeirdML–3.9%†
Terminal-Bench 4.0 (AA)Artificial Analysis10.1%1.0%†
Terminal-Bench 2.1 (AA)Artificial Analysis–55.1%†
GameBench 2 OverallDuelLab GameBench 2–25.6
GameBench 2 by reasoning settingDuelLab GameBench 2–26.8†
Design Arena CodeDesign Arena–1186
FrontierCode 1.1 (AA)Artificial Analysis–15.8%†
FrontierCode 2.0 (AA)Artificial Analysis16.6%3.9%†
Agents & tools
Terminal-BenchTerminal-Bench–0.0%†
APEX-AgentsMercor–33.8%
Arena AgentArena (LMArena)–-18.5
LiveBench Long AgenticLiveBench–9.8%†
LiveBench BrowserLiveBench–12.0%†
LiveBench Agentic CodingLiveBench–49.4%†
Terminal-Bench 2.1 (Vals)Vals AI–47.6%
MCP AtlasScale AI SEAL–76.0%†
τ³-bench Bankingτ²-bench–25.0%†
GDPval-AA v2.1Artificial Analysis15071080†
τ³-Banking (AA)Artificial Analysis–29.1%†
Analyst Agent (AA)Artificial Analysis–23.8%†
CyberBenchVals AI–66.8%
Finance Agent v2Vals AI–46.6%
Finance Agent v2.1Vals AI–49.9%
Harvey's Legal Agent Benchmark v1.1Vals AI–3.8%
Harvey's Legal Agent Benchmark v1Vals AI–2.1%
Legal Research BenchVals AI–28.4%
SkillsBenchVals AI–26.1%
SREBenchVals AI–0.0%
Tax Agent BenchVals AI–15.3%
Terminal-Bench 4.0 (Vals)Vals AI–0.5%
Arena Agent Task CompletionArena (LMArena)–-26.9
AutomationBenchArtificial Analysis48.8%5.0%†
GDP.pdf (AA)Artificial Analysis14.2%12.8%†
Harvey LAB-AA v1.1Harvey–0.0%†
EnterpriseOps-GymArtificial Analysis–38.0%†
AA-Briefcase v1.1Artificial Analysis1496833†
GDPxGDPx by SemiAnalysis–2.3%†
Design Arena AgenticDesign Arena–1162
Terminal-Bench-Science 0.1 (AA)Artificial Analysis3.8%0.0%†
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub–33.3%†
FrontierMath Tier 4Epoch AI Benchmarking Hub–4.9%†
OTIS Mock AIMEEpoch AI Benchmarking Hub–88.9%†
ProofBenchVals AI–0.0%
LiveBench MathematicsLiveBench–88.4%†
Arena MathsArena (LMArena)–1479
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub–40.3%†
LiveBench 2.0 Data AnalysisLiveBench–72.8%†
LiveBench ResearchLiveBench–60.3%†
LiveBench 1.0 Data AnalysisLiveBench–72.8%†
AA-Omniscience v1.1Artificial Analysis-11.2-1.5†
MMLU-ProVals AI–86.3%
LegalBenchVals AI–83.0%
CorpFinVals AI–68.6%
TaxEvalVals AI–75.3%
Excel Modeling BenchmarkVals AI–38.4%
Excel Modeling Benchmark v1.1Vals AI–41.0%
MedCodeVals AI–41.2%
MedScribeVals AI–85.4%
Public Benefits Bench v1.1Vals AI–58.5%
Arena Text FactualityArena (LMArena)–1452
AA-Omniscience v1.1: accuracyArtificial Analysis21.3%39.3%†
AA-Omniscience v1.1: non-hallucinationArtificial Analysis58.6%32.8%†
Instruction following
LiveBench LanguageLiveBench–73.5%†
LiveBench Instruction FollowingLiveBench–70.1%†
Arena Instruction FollowingArena (LMArena)–1427
Human preference
Arena TextArena (LMArena)–1443
EQ-Bench 4EQ-Bench–1212
EQ-Bench Creative Writing v3EQ-Bench–1609
EQ-Bench Longform WritingEQ-Bench–72.5
Arena Creative WritingArena (LMArena)–1389
Arena Multi-turnArena (LMArena)–1445
Arena Longer QueriesArena (LMArena)–1442
Multimodal
LiveBench DesignLiveBench–55.2%†
MMMU-ProArtificial Analysis78.4%73.5%†
MMMU-Pro (Vals)Vals AI–78.5%
MortgageTaxVals AI–64.0%
AudioMCScale AI SEAL–56.6%†
AudioMC (text output)Scale AI SEAL–56.6%†
Code2Video-AAArtificial Analysis–467†
AA-3DArtificial Analysis–591†
Long context
AA-LCR v1.1Artificial Analysis84.7%77.3%†
MLCRArtificial Analysis–6.1%†
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub–148.4
LiveBench 2.0LiveBench–44.3%†
LiveBench 1.0LiveBench–71.9%†
AA Intelligence Index v5.0.1Artificial Analysis24.012.5†
AA Intelligence Index v4.3.2Artificial Analysis–25.0†
AA Progress Index v1Artificial Analysis304.2281.4†
Vals IndexVals AI–29.0
Vals Finance IndexVals AI–38.3%
Vals Multimodal IndexVals AI–49.4%
Vals Router IndexVals AI–29.0%
Vals Legal IndexVals AI–54.2%
Safety & honesty
FORTRESSScale AI SEAL–25.0%†
DistressBenchScale AI SEAL–78.5%
Metadata
AA Openness IndexArtificial Analysis–38.9†

Data as of 2026-11-21. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261119-1d7fd529faf6 (https://benchmarks.duellab.org/releases/gb2-20261119-1d7fd529faf6/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • Agnes 2.5 Pro Theta: 1 new result (AA Progress Index v1).
  • Inkling: 1 score revision.
  • Inkling: 2 score revisions.
  • Inkling: BenchLeader Index 47.8 → 50.4.
  • Inkling: 1 score revision.
  • Agnes 2.5 Pro Theta: first results.
  • Inkling: 5 score revisions.
  • Inkling: 1 score revision.
  • Inkling: 1 score revision.

Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs

Agnes 2.5 Pro Theta vs Inkling: questions

Is Agnes 2.5 Pro Theta better than Inkling?
Agnes 2.5 Pro Theta and Inkling are neck and neck on quality (50.7 vs 50.2, within the ±10.5 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 21 Nov 2026, so check the category scores for your use.
Agnes 2.5 Pro Theta vs Inkling: which is cheaper, and will that change?
Agnes 2.5 Pro Theta is cheaper today: $0.150 against $2.57 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Agnes 2.5 Pro Theta or Inkling better for coding?
They are level in coding (45 vs 46 on the category index).
Which is faster, Agnes 2.5 Pro Theta or Inkling?
Agnes 2.5 Pro Theta streams ~1.5× faster (189 vs 110 output tokens per second, Artificial Analysis 7-day median).
Which is better for long documents?
Agnes 2.5 Pro Theta accepts more context: 1,000,000 against 65,536 tokens for Inkling.
More questions (2)
Which has lower latency?
Inkling answers first: 0.2 s against 8.8 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
When was Agnes 2.5 Pro Theta released?
Agnes 2.5 Pro Theta was released on 7 Nov 2026.