BasedAGIBasedAGI

Model Profile

kimi/kimi-k2.5-thinking

External Benchmark Shadowexternal_benchmark_shadowpublic
4,096 ctx

Use this page to decide where this model is a strong fit. Rankings below are benchmark-backed by use case, with explicit confidence and contributor metrics.

Identity

ID: external/kimi/kimi-k2-5-thinking

Author: kimi

Origin: external_benchmark_shadow

Arch: unknown

Benchmark Coverage

Scored use cases: 12

Avg confidence: 30.1%

Evidence points: 245

Raw rows: 507

Weighted rows: 55

Catalog Metadata

Parameters: unknown

Context window: 4096

Downloads: 0

Intelligence Profile

IQ68%EQ *0%Accuracy *29%Creativity *92%Based *59%

Dimension Breakdown

IQ24 benchmarks
68.0%
EQ1 benchmark
0.0%*
Accuracy8 benchmarks
29.2%*
Creativity2 benchmarks
92.1%*
Based1 benchmark
59.0%*

* Low confidence — limited benchmark evidence for this dimension

5/5 dimensions scored · Last updated Apr 21, 2026

Benchmark Signals

Click through to the benchmark source behind this model profile.

Some fit rows have limited benchmark evidence.

1 of 12 scored use cases have low confidence or thin contributor coverage.

Coverage Diagnostics

actively scored

Use-Case Scores

146

Total Measurements

507

Weighted Measurements

55

Weighted Sources

28

Raw Source Coverage

ugi_main 60vals_finance_agent 40vals_multimodal_index 32corpfin_taxeval_public 28vals_medqa 28vals_vals_index 24

Weighted Source Coverage

openhands_index 5vals_finance_agent 5basedagi_doc_summarization_eval 4basedagi_kb_qna_eval 4basedagi_log_triage_eval 4basedagi_support_bot_eval 4

Best Use Cases for This Model

Use CaseScore
Thesis red teaming

use_case.fin.thesis_red_team

28.6%
Accounts payable invoice extraction (text)

use_case.fin.ap_invoice_extraction

26.6%
Earnings call synthesis

use_case.fin.earnings_call_synthesis

25.8%
Transaction anomaly narrative

use_case.fin.transaction_anomaly_narrative

25.3%
AML alert triage

use_case.fin.aml_alert_triage

24.3%
KYC profile synthesis

use_case.fin.kyc_profile_synthesis

24.3%
Filings summarization (10-K/10-Q)

use_case.fin.filings_summarization

22.5%
Quant research code generation

use_case.fin.alpha_research_codegen

21.6%
Screenplay scene writing

use_case.creative.screenplay_scene

21.3%
Poetry and lyrics

use_case.creative.poetry_lyrics

21.3%
Runbook step assistant

use_case.sre.runbook_steps

18.6%
Component selection assistant

use_case.eng.component_selection

18.5%