Skip to main content

Model profile

Agents-A1

Data verified
Overall Score
Unranked
Arena Elo
Not listed
Eligible category ranks
2of 8
Price (1M tokens)
Not listedAPI pricing
Speed
Not listed
Context
262K

Evidence coverage

6 of 323 tracked benchmarks are published. 6 are verified and 0 provisional. 4 of 8 categories are measured.

Updated July 23, 2026Methodology
Published / tracked
6 / 323
Verified
6
Provisional
0
Categories with evidence
4 / 8

Evidence by category

  • Agentic3 benchmarks
    Verified
  • Coding0 benchmarks
    Not measured
  • Reasoning1 benchmark
    Verified
  • Knowledge1 benchmark
    Verified
  • Math0 benchmarks
    Not measured
  • Multilingual0 benchmarks
    Not measured
  • Multimodal0 benchmarks
    Not measured
  • Inst. Following1 benchmark
    Verified
Open WeightSelf-hostReasoning
Confidence:
Low
base

BenchLM is tracking Agents-A1, but this profile is currently excluded from the public leaderboard because it still lacks enough non-generated benchmark coverage to rank safely. Only non-generated public benchmark rows appear below.

Agents-A1 is a open weight model with a 262K token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.

Agents-A1 sits inside the Agents-A1 family alongside Agents-A1-F16-GGUF, Agents-A1-FP8, Agents-A1-Q4_K_M-GGUF, Agents-A1-Q8_0-GGUF. This profile currently has 6 of 323 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Instruction Following (#3), while its weakest is Agentic (#34). This performance profile makes it a well-rounded choice across a range of tasks.

Peer position

Exact provisional scores and ranks for the closest listed peers. A score can appear before a model clears the evidence threshold for a rank, so equal scores can have different rank states.

Range 77.4483.93

  1. Claude Mythos 5
    Anthropic
    #183.93
    Claude Mythos 5 is #1 with a score of 83.93.
    Compare
  2. Claude Fable 5
    Anthropic
    #283.68
    Claude Fable 5 is #2 with a score of 83.68.
    Compare
  3. GPT-5.6 Sol
    OpenAI
    #381.96
    GPT-5.6 Sol is #3 with a score of 81.96.
    Compare
  4. Kimi K3
    Moonshot AI
    #480.96
    Kimi K3 is #4 with a score of 80.96.
    Compare
  5. Claude Opus 4.8
    Anthropic
    #578.34
    Claude Opus 4.8 is #5 with a score of 78.34.
    Compare
  6. Muse Spark 1.1
    Meta
    #677.44
    Muse Spark 1.1 is #6 with a score of 77.44.
    Compare
  7. Agents-A1Current model
    InternScience
    UnrankedNot measured
    Agents-A1 is Unranked with a score of Not measured.

Category percentile

More

Relative position among models eligible for each sourced category. A higher percentile means a stronger position within that category's ranked cohort; 100 is highest.

  1. Inst. Following93%
    Eligible cohort rank #3 of 31Category score 93.0
  2. Agentic72%
    Eligible cohort rank #34 of 119Category score 52.3

Category evidence

Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank #34 of 119Percentile 72ndWeight 22%3 benchmarksVerified52.3
CodingWeight 20%0 benchmarksNot measuredNot measured
ReasoningRank Not rankedWeight 17%1 benchmarkVerified76.2
KnowledgeRank Not rankedWeight 12%1 benchmarkVerified74.1
MathWeight 5%0 benchmarksNot measuredNot measured
MultilingualWeight 7%0 benchmarksNot measuredNot measured
MultimodalWeight 12%0 benchmarksNot measuredNot measured
Inst. FollowingRank #3 of 31Percentile 93rdWeight 5%1 benchmarkVerified93.0

Benchmark Details

Rows below have a displayable published verification record. Each source link and provenance note remains in the page HTML while its category is closed. Source-unverified manual rows and generated rows stay hidden.

Agentic3 benchmarks
BrowseCompProvider exact
75.5%Weighted 28%
Source: InternScience Agents-A1 model cardProvenance: Provider exact
HLE w/ toolsProvider exact

Humanity's Last Exam with tools

47.6%Display only
Source: InternScience Agents-A1 model cardProvenance: Provider exact
VITA-BenchProvider exact
38.8%Display only
Source: InternScience Agents-A1 model cardProvenance: Provider exact
Reasoning1 benchmark
LongBench v2Provider exact
60.2%Weighted 38%
Source: InternScience Agents-A1 model cardProvenance: Provider exact
Knowledge1 benchmark
HLEProvider exact

Humanity's Last Exam

47.6%Weighted 45%
Source: InternScience Agents-A1 model cardProvenance: InternScience reports HLE with tools at 47.6. BenchLM stores the same exact row on the core HLE key for sparse knowledge comparison and on hleWithTools for agentic display.
Inst. Following1 benchmark
IFEvalProvider exact

Instruction-Following Eval

94.8%Weighted 35%
Source: InternScience Agents-A1 model cardProvenance: Provider exact

Frequently Asked Questions

How does Agents-A1 perform overall in AI benchmarks?

Agents-A1 has 6 published benchmark scores on BenchLM, but it does not yet have enough non-generated coverage to receive a global overall rank.

Is Agents-A1 good for knowledge and understanding?

Agents-A1 has visible benchmark coverage in knowledge and understanding, but BenchLM does not currently assign it a global category rank there.

Is Agents-A1 good for reasoning and logic?

Agents-A1 has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.

Is Agents-A1 good for agentic tool use and computer tasks?

Agents-A1 ranks #34 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 52.3. There are stronger options in this category.

Is Agents-A1 good for instruction following?

Agents-A1 ranks #3 out of 31 models in instruction following benchmarks with an average score of 93. It is among the top performers in this category.

Is Agents-A1 open source?

Yes, Agents-A1 is an open weight model created by InternScience, meaning it can be downloaded and run locally or fine-tuned for specific use cases.

Which sibling models are related to Agents-A1?

Agents-A1 belongs to the Agents-A1 family. Related variants on BenchLM include Agents-A1-F16-GGUF, Agents-A1-FP8, Agents-A1-Q4_K_M-GGUF, Agents-A1-Q8_0-GGUF.

Does Agents-A1 have full benchmark coverage on BenchLM?

Not yet. Agents-A1 currently has 6 published benchmark scores out of the 323 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of Agents-A1?

Agents-A1 has a published context window of 262K, which determines how much text it can process in a single interaction.

Last updated: July 23, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Choose with this week’s evidence

Join 2,000+ readers for ranking moves, new releases, pricing changes, and the evidence behind them.

Free. One email per week.