Geopolitics

Political risk brief

Summarize key developments into risks, scenarios, and actions.

task.write_memo_brieftask.risk_assessment

Evidence quality is currently limited for this use case. Rankings below are useful for exploration, not a strong winner claim.

Provisional leader

gemini-3.1-pro-preview

Current leader based on limited benchmark evidence. Treat this ranking as directional until coverage improves.

31.9%

Best benchmark score

36.3%

Confidence

All ranked models — top 3

🥇

gemini-3.1-pro-preview

31.9%

🥈

claude-sonnet-4

28.5%

🥉

gpt-5-2025-08-07

27.6%

Ranked Models

Evidence Quality

83%

Evidence Points

Top Signal

Vals Finance Agent: overall_accuracy_pct

All Ranked Models

30 of 30 models

Rank	Model	Score	Confidence	Price / 1M	Evidence sources
🥇	gemini-3.1-pro-preview Strong on Vals Finance Agent overall_accuracy_pct and FACTS Benchmark Suite facts_search_score_pct	31.9%	36%	$4.50	Vals Finance AgentFACTS Benchmark Suite
🥈	claude-sonnet-4 Strong on LanguageBench overall:mean and Vectara HHEM Leaderboard overall_hallucination_error_pct	28.5%	44%	$6.00	LanguageBenchVectara HHEM Leaderboard
🥉	gpt-5-2025-08-07 Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals Finance Agent overall_accuracy_pct	27.6%	38%	—	FACTS Benchmark SuiteVals Finance Agent
#4	gemini-2.5-pro Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct	27.3%	49%	$3.44	FACTS Benchmark SuiteVectara HHEM Leaderboard
#5	gemini-2.5-flash Strong on LanguageBench overall:mean and FACTS Benchmark Suite facts_grounding_score_pct	25.7%	37%	$0.17	LanguageBenchFACTS Benchmark Suite
#6	gpt-5-mini-2025-08-07 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	25.2%	40%	—	Vals Finance AgentVals CorpFin v2
#7	gemini-3-pro-preview Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	24.6%	34%	$4.50	Vals Finance AgentVals CorpFin v2
#8	gemini-3-flash-preview Strong on Vals CorpFin v2 overall_accuracy_pct and FACTS Benchmark Suite facts_grounding_score_pct	24.4%	33%	$1.13	Vals CorpFin v2FACTS Benchmark Suite
#9	gpt-5.2-2025-12-11 Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals CorpFin v2 overall_accuracy_pct	23.8%	29%	—	FACTS Benchmark SuiteVals CorpFin v2
#10	Grok-4-0709 Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	23.1%	33%	—	Vals CorpFin v2Vals Finance Agent
#11	gemini-3.1-flash-lite-preview Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct	22.7%	35%	$0.56	FACTS Benchmark SuiteVectara HHEM Leaderboard
#12	claude-sonnet-4.6 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	22.2%	28%	$6.00	Vals Finance AgentVals CorpFin v2
#13	gpt-5.4-2026-03-05 Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and Vals CorpFin v2 overall_accuracy_pct	20.9%	26%	—	Vectara HHEM LeaderboardVals CorpFin v2
#14	claude-opus-4-5-20251101 Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals CorpFin v2 overall_accuracy_pct	20.0%	29%	—	FACTS Benchmark SuiteVals CorpFin v2
#15	gpt-4.1-20250414 Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and Vals CorpFin v2 overall_accuracy_pct	19.7%	30%	—	Vectara HHEM LeaderboardVals CorpFin v2
#16	gpt-5.1-2025-11-13 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	18.8%	29%	—	Vals Finance AgentVals CorpFin v2
#17	grok-4-fast-reasoning Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	18.7%	36%	$0.28	Vals CorpFin v2Vals Finance Agent
#18	o3-20250416 Strong on Vals CorpFin v2 overall_accuracy_pct and SciArena Leaderboard rating_elo	18.1%	28%	$3.50	Vals CorpFin v2SciArena Leaderboard
#19	kimi-k2.5-thinking Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	15.9%	23%	—	Vals CorpFin v2Vals Finance Agent
#20	Claude-3.5-Sonnet Strong on LanguageBench overall:mean and LLM-AggreFact Leaderboard average_score_pct	15.7%	24%	$6.00	LanguageBenchLLM-AggreFact Leaderboard
#21	claude-opus-4-5-20251101-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	15.6%	19%	—	Vals Finance AgentVals CorpFin v2
#22	claude-opus-4-6-thinking Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	15.5%	17%	—	Vals CorpFin v2Vals Finance Agent
#23	grok-4-1-fast-reasoning Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	15.4%	23%	$0.28	Vals CorpFin v2Vals Finance Agent
#25	grok-3 Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and Vals CorpFin v2 overall_accuracy_pct	14.5%	20%	$6.00	Vectara HHEM LeaderboardVals CorpFin v2
#26	claude-sonnet-4-5-20250929-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	14.0%	19%	—	Vals Finance AgentVals CorpFin v2
#27	gpt-4.1 Strong on LanguageBench overall:mean and LanguageBench Translation Official (Split) translation_to:bleu	13.9%	19%	$3.50	LanguageBenchLanguageBench Translation Official (Split)
#30	grok-4.20-0309-reasoning Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	13.2%	17%	—	Vals CorpFin v2Vals Finance Agent
#31	glm-5-thinking Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	13.1%	19%	—	Vals CorpFin v2Vals Finance Agent
#32	gemini-2.0-flash-001 Strong on LanguageBench overall:mean and LanguageBench Translation Official (Split) translation_to:bleu	12.9%	20%	—	LanguageBenchLanguageBench Translation Official (Split)
#34	mistral-large-2512 Strong on Vals CorpFin v2 overall_accuracy_pct and Vectara HHEM Leaderboard overall_answer_rate_pct	12.1%	22%	—	Vals CorpFin v2Vectara HHEM Leaderboard

Compare Models

Select two different models above to compare their evidence side by side.

▶Ranking diagnostics & missing models

Source lift

Ranked

Sources

Quality

Low

Vals CorpFin v2

44 rows · 1.6% avg lift

Vals MedQA

36 rows · 0.4% avg lift

Vals Legal Bench

35 rows · 0.4% avg lift

Vals Tax Eval v2

35 rows · 0.4% avg lift

Missing frontier models

No obvious gaps right now.

▶Taxonomy & task details

Core tasks

task.write_memo_brieftask.risk_assessment

Required modes

none

Domains

domain.geopolitics_intel

Related in Geopolitics

Narrative tracking

Track narratives across multi-lingual sources and flag contradictions.