BenchLeader

Agnes 2.5 Pro Theta vs Apodex 1.1

Full profiles: Agnes 2.5 Pro Theta (Sapiens AI) and Apodex 1.1 (Apodex): every benchmark, price and rank.

Updated · Data from 1 sources

As of 21 Nov 2026, Agnes 2.5 Pro Theta and Apodex 1.1 are neck and neck on quality (50.7 vs 48.1 on the BenchLeader Index, inside the ±12.2 margin), and Agnes 2.5 Pro Theta is 6.5× cheaper at $0.150 vs $0.975 per 1M tokens blended. Agnes 2.5 Pro Theta leads in every category we measure both in.

Key facts (as of 21 Nov 2026)

  • Agnes 2.5 Pro Theta scores 50.7 on the BenchLeader Index and Apodex 1.1 scores 48.1 (BenchLeader, 21 Nov 2026).
  • Agnes 2.5 Pro Theta costs $0.150 per 1M tokens blended (list price, 21 Nov 2026).
  • Apodex 1.1 costs $0.975 per 1M tokens blended (list price, 21 Nov 2026).
  • Of the 18 benchmarks both models have, Agnes 2.5 Pro Theta leads 16 (BenchLeader, 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
CodingAgnes 2.5 Pro Theta45 vs 36 category score; FrontierCode 2.0 (AA) 16.6% vs 6.9%High
ReasoningAgnes 2.5 Pro Theta43 vs 39 category score; HLE-Diamond (AA) 16.8% vs 11.6%Medium
KnowledgeAgnes 2.5 Pro Theta40 vs 31 category score; AA-Omniscience v1.1 -11.2 vs -27.9High
Long documentsAgnes 2.5 Pro Theta67 vs 64 category score; AA-LCR v1.1 84.7% vs 79.3%Medium
Images and other mediaEither60 vs 61 category score; MMMU-Pro 78.4% vs 79.2%Either
Lowest costAgnes 2.5 Pro Theta$0.150 vs $0.975 per 1M blended; agentic coding session $0.007 vs $0.030–
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 Apodex 1.1 are neck and neck on quality (50.7 vs 48.1, within the ±12.2 margin).
  • Agnes 2.5 Pro Theta is stronger in coding, knowledge, long context, reasoning.
  • Apodex 1.1 is stronger in multimodal.
  • Agnes 2.5 Pro Theta is 6.5× cheaper ($0.150 vs $0.975 per 1M blended).

At a glance

SpecAgnes 2.5 Pro ThetaApodex 1.1
DeveloperSapiens AIApodex
Released7 Nov 202630 Aug 2026
Context window (tokens)1,000,000256,000
Compared atAgnes 2.5 Pro ThetaApodex 1.1
Open weightsNoNo
Price in / out / cached input per 1M$0.100 / $0.300 / $0.010$0.300 / $3.00 / $0.030

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 ThetaApodex 1.1Leader
Reasoning43.238.5Agnes 2.5 Pro Theta
Coding45.335.7Agnes 2.5 Pro Theta
Agents & tools–53.3not comparable
Knowledge39.531.1Agnes 2.5 Pro Theta
Multimodal60.461.2level
Long context67.164.3Agnes 2.5 Pro Theta

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 avg75ReasoningCodingKnowledgeLong contextMultimodalAgnes 2.5 Pro Theta, Reasoning: 43.2Agnes 2.5 Pro Theta, Coding: 45.3Agnes 2.5 Pro Theta, Knowledge: 39.5Agnes 2.5 Pro Theta, Long context: 67.1Agnes 2.5 Pro Theta, Multimodal: 60.4Apodex 1.1, Reasoning: 38.5Apodex 1.1, Coding: 35.7Apodex 1.1, Knowledge: 31.1Apodex 1.1, Long context: 64.3Apodex 1.1, Multimodal: 61.2

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

Model, click to add or removeIndex

Where sources disagree

Across the 18 benchmarks both have, Agnes 2.5 Pro Theta leads 16, Apodex 1.1 leads 2. Every overall index that rates both puts Agnes 2.5 Pro Theta ahead.

Overall indexAgnes 2.5 Pro ThetaApodex 1.1Leader
BenchLeader Index50.748.1neck and neck
AA Intelligence Index v5.0.124.013.7Agnes 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 ThetaApodex 1.1
Blended price per 1M tokens$0.150$0.975
Input / output per 1M$0.100 / $0.300$0.300 / $3.00
Cached input per 1M$0.010$0.030
Price per task: chat reply$0.0001$0.0010
Price per task: summarize a 30-page report$0.0014$0.0054
Price per task: code edit$0.0011$0.0063
Price per task: agentic coding session$0.0072$0.030
Price per task: structured extraction$0.0003$0.0012
Agentic coding session, input mostly cached$0.0032$0.018
Cost per benchmark task (AA Index)$0.575$0.764
Output tokens per task (AA Index)278k116k
Of which reasoning229k76k
Time per task (AA Index)24 min–
Output speed189 tok/s–
Time to first answer8.8 s–
Time to a complete answer, last measured 13 Nov 202616.9 s45.0 s

Per token is not per task: an average task of Artificial Analysis' Intelligence Index cost $0.575 on Agnes 2.5 Pro Theta and $0.764 on Apodex 1.1, and Agnes 2.5 Pro Theta wrote 2.4× as many output tokens for the same work, which a per-token price hides.

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. Apodex 1.1 scores 48.1. 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

25 benchmarks, grouped by category; each name links to the board and its leaders.

MetricPublisherAgnes 2.5 Pro ThetaApodex 1.1
BenchLeader IndexBenchLeader50.748.1
Coding scoreBenchLeader45.335.7
Knowledge scoreBenchLeader39.531.1
Long context scoreBenchLeader67.164.3
Multimodal scoreBenchLeader60.461.2
Reasoning scoreBenchLeader43.238.5
Agents & tools scoreBenchLeader–53.3
Blended price $/MBenchLeader$0.150$0.975
Output speedBenchLeader189 tok/s–
Time to first answerBenchLeader8.8 s–
Context windowBenchLeader1,000,000 tokens256,000 tokens
Reasoning
GPQA Diamond (AA)Artificial Analysis–86.4%
Humanity's Last Exam (AA)Artificial Analysis37.2%34.1%
HLE-Diamond (AA)Artificial Analysis16.8%11.6%
CritPtArtificial Analysis15.1%4.6%
CritPt v2 hard subset (AA)Artificial Analysis26.0%17.0%
Coding
SciCode (AA)Artificial Analysis56.0%45.5%
Terminal-Bench 4.0 (AA)Artificial Analysis10.1%0.0%
Terminal-Bench 2.1 (AA)Artificial Analysis–69.7%
FrontierCode 2.0 (AA)Artificial Analysis16.6%6.9%
Agents & tools
GDPval-AA v2.1, normalised scoreArtificial Analysis–34.4%
GDPval-AA v2.1Artificial Analysis15071195
τ³-Banking (AA)Artificial Analysis–25.1%
APEX-Agents (AA)Artificial Analysis–31.2%
AutomationBenchArtificial Analysis48.8%28.2%
GDP.pdf (AA)Artificial Analysis14.2%11.2%
AA-Briefcase v1.1Artificial Analysis14961014
Terminal-Bench-Science 0.1 (AA)Artificial Analysis3.8%0.5%
Knowledge
AA-Omniscience v1.1Artificial Analysis-11.2-27.9
AA-Omniscience v1.1: accuracyArtificial Analysis21.3%28.2%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis58.6%22.0%
Multimodal
MMMU-ProArtificial Analysis78.4%79.2%
Long context
AA-LCR v1.1Artificial Analysis84.7%79.3%
Composite
AA Intelligence Index v5.0.1Artificial Analysis24.013.7
AA Intelligence Index v4.3.2Artificial Analysis–26.4
AA Progress Index v1Artificial Analysis304.2291.7

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

What changed

  • Agnes 2.5 Pro Theta: 1 new result (AA Progress Index v1).
  • Apodex 1.1: BenchLeader Index 48.3 → 47.7.
  • Apodex 1.1: 2 new results (AA Intelligence Index v5.0.1, CritPt v2 hard subset (AA)).
  • Apodex 1.1: 4 new results (AA-Omniscience v1.1, AA-Omniscience v1.1: accuracy, AA-Omniscience v1.1: non-hallucination…).
  • Agnes 2.5 Pro Theta: first results.
  • Apodex 1.1: 1 new result (Terminal-Bench-Science 0.1 (AA)).
  • Apodex 1.1: 1 new result (AA-Briefcase v1.1).
  • Apodex 1.1: 2 new results (AA Progress Index v1, HLE-Diamond (AA)).

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

Agnes 2.5 Pro Theta vs Apodex 1.1: questions

Is Agnes 2.5 Pro Theta better than Apodex 1.1?
Agnes 2.5 Pro Theta and Apodex 1.1 are neck and neck on quality (50.7 vs 48.1, within the ±12.2 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 Apodex 1.1: which is cheaper, and will that change?
Agnes 2.5 Pro Theta is cheaper today: $0.150 against $0.975 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 Apodex 1.1 better for coding?
Agnes 2.5 Pro Theta scores higher in coding (45 vs 36 on the category index, where 50 is average). On FrontierCode 2.0 (AA), the top shared coding benchmark, it is 16.6% for Agnes 2.5 Pro Theta against 6.9% for Apodex 1.1.
Which is better for long documents?
Agnes 2.5 Pro Theta scores higher on long-context benchmarks (67 vs 64). Agnes 2.5 Pro Theta accepts more context: 1,000,000 against 256,000 tokens for Apodex 1.1.
Do independent benchmarks agree on Agnes 2.5 Pro Theta vs Apodex 1.1?
Across the 18 benchmarks both have, Agnes 2.5 Pro Theta leads 16, Apodex 1.1 leads 2. Every overall index that rates both puts Agnes 2.5 Pro Theta ahead.
More questions (1)
When was Agnes 2.5 Pro Theta released?
Agnes 2.5 Pro Theta was released on 7 Nov 2026.