GPT-4.1 Nano

openai/gpt-4.1-nano-2025-04-14

OpenAI's GPT-4.1 Nano, released on 2025-04-14, accepts image, text, and file inputs and generates text output. It provides a context window of 1,047,576 tokens, costs $0.10 per million input tokens and $0.40 per million output tokens, supports tool usage but does not support reasoning, and its weights are not open.

tool use
structured outputs

At a glance

provideropenai

releasedApr 14, 2025

context1.0M

input / M$0.100

Specifications

What the API gives you

Context window: 1.0M tokens
Max output: 33K tokens
Input price: $0.100 / 1M tokens
Output price: $0.40 / 1M tokens
Cache read: $0.025 / 1M tokens
Modalities: image, text, file → text
Knowledge cutoff: Jun 30, 2024
Released: Apr 14, 2025

Measured evidence

Public benchmark record

Aider Polyglot: 8.9%2026-07-17
Aider Polyglot: 8.9%2026-07-21
Aider Polyglot: 8.9%2026-07-23
Aider Polyglot: 8.9%2026-07-27
Aider Polyglot: 8.9%2026-07-28
Aider Polyglot: 8.9%2026-07-29
Aider Polyglot: 8.9%2026-07-30
Aider Polyglot: 8.9%2026-07-31
Aider Polyglot: 8.9%2026-08-01
Aider Polyglot: 8.9%2026-08-02
Aider Polyglot: 8.9%2026-08-05
Aider Polyglot: 8.9%2026-08-03
Aider Polyglot: 8.9%2026-08-09
Aider Polyglot: 8.9%2026-08-04
Aider Polyglot: 8.9%2026-08-06
Aider Polyglot: 8.9%2026-08-07
Aider Polyglot: 8.9%2026-08-14
Aider Polyglot: 8.9%2026-08-08
Aider Polyglot: 8.9%2026-08-10
Aider Polyglot: 8.9%2026-08-11
Aider Polyglot: 8.9%2026-08-15
Aider Polyglot: 8.9%2026-08-18
Aider Polyglot: 8.9%2026-08-12
Aider Polyglot: 8.9%2026-08-19
Aider Polyglot: 8.9%2026-08-13
Aider Polyglot: 8.9%2026-08-20
Aider Polyglot: 8.9%2026-08-16
Aider Polyglot: 8.9%2026-08-17
Aider Polyglot: 8.9%2026-08-21
Aider Polyglot: 8.9%2026-08-27
Aider Polyglot: 8.9%2026-08-22
Aider Polyglot: 8.9%2026-08-23
Aider Polyglot: 8.9%2026-08-24
Aider Polyglot: 8.9%2026-08-25
Aider Polyglot: 8.9%2026-09-05
Aider Polyglot: 8.9%2026-08-26
Aider Polyglot: 8.9%2026-08-28
Aider Polyglot: 8.9%2026-09-06
Aider Polyglot: 8.9%2026-08-29
Aider Polyglot: 8.9%2026-08-30
Aider Polyglot: 8.9%2026-08-31
Aider Polyglot: 8.9%2026-09-01
Aider Polyglot: 8.9%2026-09-02
Aider Polyglot: 8.9%2026-09-03
Aider Polyglot: 8.9%2026-09-04
BFCL: 33.0%2026-07-28
BFCL: 33.0%2026-07-27
BFCL: 33.0%2026-07-29
BFCL: 33.0%2026-07-30
BFCL: 33.0%2026-07-31
BFCL: 33.0%2026-08-02
BFCL: 33.0%2026-08-01
BFCL: 33.0%2026-08-05
BFCL: 33.0%2026-08-03
BFCL: 33.0%2026-08-09
BFCL: 33.0%2026-08-04
BFCL: 33.0%2026-08-06
BFCL: 33.0%2026-08-07
BFCL: 33.0%2026-08-10
BFCL: 33.0%2026-08-14
BFCL: 33.0%2026-08-08
BFCL: 33.0%2026-08-11
BFCL: 33.0%2026-08-18
BFCL: 33.0%2026-08-15
BFCL: 33.0%2026-08-12
BFCL: 33.0%2026-08-13
BFCL: 33.0%2026-08-19
BFCL: 33.0%2026-08-16
BFCL: 33.0%2026-08-20
BFCL: 33.0%2026-08-27
BFCL: 33.0%2026-08-17
BFCL: 33.0%2026-08-21
BFCL: 33.0%2026-08-22
BFCL: 33.0%2026-08-23
BFCL: 33.0%2026-08-24
BFCL: 33.0%2026-09-05
BFCL: 33.0%2026-08-28
BFCL: 33.0%2026-08-25
BFCL: 33.0%2026-08-26
BFCL: 33.0%2026-09-06
BFCL: 33.0%2026-08-29
BFCL: 33.0%2026-08-30
BFCL: 33.0%2026-08-31
BFCL: 33.0%2026-09-01
BFCL: 33.0%2026-09-02
BFCL: 33.0%2026-09-03
BFCL: 33.0%2026-09-04
Design Arena Coding: 993 Elo2026-07-28
Design Arena Coding: 993 Elo2026-07-27
Design Arena Coding: 993 Elo2026-07-30
Design Arena Coding: 993 Elo2026-07-29
Design Arena Coding: 993 Elo2026-07-31
Design Arena Coding: 992 Elo2026-08-02
Design Arena Coding: 991 Elo2026-08-05
Design Arena Coding: 992 Elo2026-08-01
Design Arena Coding: 991 Elo2026-08-09
Design Arena Coding: 992 Elo2026-08-03
Design Arena Coding: 992 Elo2026-08-04
Design Arena Coding: 988 Elo2026-08-14
Design Arena Coding: 992 Elo2026-08-06
Design Arena Coding: 990 Elo2026-08-10
Design Arena Coding: 992 Elo2026-08-07
Design Arena Coding: 982 Elo2026-08-18
Design Arena Coding: 991 Elo2026-08-08
Design Arena Coding: 982 Elo2026-08-15
Design Arena Coding: 991 Elo2026-08-11
Design Arena Coding: 990 Elo2026-08-12
Design Arena Coding: 988 Elo2026-08-13
Design Arena Coding: 981 Elo2026-08-19
Design Arena Coding: 987 Elo2026-08-27
Design Arena Coding: 981 Elo2026-08-20
Design Arena Coding: 982 Elo2026-08-16
Design Arena Coding: 979 Elo2026-09-05
Design Arena Coding: 982 Elo2026-08-17
Design Arena Coding: 987 Elo2026-08-21
Design Arena Coding: 987 Elo2026-08-22
Design Arena Coding: 987 Elo2026-08-23
Design Arena Coding: 987 Elo2026-08-28
Design Arena Coding: 988 Elo2026-08-24
Design Arena Coding: 988 Elo2026-08-25
Design Arena Coding: 988 Elo2026-08-26
Design Arena Coding: 979 Elo2026-09-06
Design Arena Coding: 987 Elo2026-08-29
Design Arena Coding: 986 Elo2026-08-30
Design Arena Coding: 986 Elo2026-08-31
Design Arena Coding: 987 Elo2026-09-01
Design Arena Coding: 985 Elo2026-09-02
Design Arena Coding: 983 Elo2026-09-03
Design Arena Coding: 982 Elo2026-09-04
Design Arena UI: 953 Elo2026-07-28
Design Arena UI: 953 Elo2026-07-27
Design Arena UI: 953 Elo2026-07-30
Design Arena UI: 953 Elo2026-07-29
Design Arena UI: 953 Elo2026-07-31
Design Arena UI: 953 Elo2026-08-02
Design Arena UI: 953 Elo2026-08-01
Design Arena UI: 952 Elo2026-08-05
Design Arena UI: 953 Elo2026-08-03
Design Arena UI: 949 Elo2026-08-09
Design Arena UI: 952 Elo2026-08-04
Design Arena UI: 947 Elo2026-08-14
Design Arena UI: 951 Elo2026-08-06
Design Arena UI: 951 Elo2026-08-07
Design Arena UI: 949 Elo2026-08-10
Design Arena UI: 949 Elo2026-08-08
Design Arena UI: 943 Elo2026-08-18
Design Arena UI: 949 Elo2026-08-11
Design Arena UI: 944 Elo2026-08-15
Design Arena UI: 949 Elo2026-08-12
Design Arena UI: 950 Elo2026-08-13
Design Arena UI: 943 Elo2026-08-19
Design Arena UI: 944 Elo2026-08-16
Design Arena UI: 943 Elo2026-08-20
Design Arena UI: 942 Elo2026-08-27
Design Arena UI: 943 Elo2026-08-17
Design Arena UI: 938 Elo2026-09-05
Design Arena UI: 942 Elo2026-08-21
Design Arena UI: 943 Elo2026-08-22
Design Arena UI: 943 Elo2026-08-23
Design Arena UI: 943 Elo2026-08-24
Design Arena UI: 942 Elo2026-08-28
Design Arena UI: 943 Elo2026-08-25
Design Arena UI: 943 Elo2026-08-26
Design Arena UI: 939 Elo2026-09-06
Design Arena UI: 942 Elo2026-08-29
Design Arena UI: 942 Elo2026-08-30
Design Arena UI: 942 Elo2026-08-31
Design Arena UI: 942 Elo2026-09-01
Design Arena UI: 941 Elo2026-09-02
Design Arena UI: 939 Elo2026-09-03
Design Arena UI: 938 Elo2026-09-04
Design Arena Website: 998 Elo2026-07-28
Design Arena Website: 998 Elo2026-07-30
Design Arena Website: 998 Elo2026-07-27
Design Arena Website: 998 Elo2026-07-29
Design Arena Website: 997 Elo2026-07-31
Design Arena Website: 997 Elo2026-08-02
Design Arena Website: 996 Elo2026-08-01
Design Arena Website: 996 Elo2026-08-05
Design Arena Website: 997 Elo2026-08-03
Design Arena Website: 995 Elo2026-08-09
Design Arena Website: 996 Elo2026-08-04
Design Arena Website: 992 Elo2026-08-14
Design Arena Website: 996 Elo2026-08-06
Design Arena Website: 996 Elo2026-08-07
Design Arena Website: 995 Elo2026-08-10
Design Arena Website: 995 Elo2026-08-08
Design Arena Website: 984 Elo2026-08-18
Design Arena Website: 995 Elo2026-08-11
Design Arena Website: 984 Elo2026-08-15
Design Arena Website: 994 Elo2026-08-12
Design Arena Website: 993 Elo2026-08-13
Design Arena Website: 984 Elo2026-08-19
Design Arena Website: 984 Elo2026-08-16
Design Arena Website: 984 Elo2026-08-20
Design Arena Website: 992 Elo2026-08-27
Design Arena Website: 984 Elo2026-08-17
Design Arena Website: 988 Elo2026-09-05
Design Arena Website: 992 Elo2026-08-21
Design Arena Website: 993 Elo2026-08-22
Design Arena Website: 993 Elo2026-08-23
Design Arena Website: 993 Elo2026-08-24
Design Arena Website: 993 Elo2026-08-28
Design Arena Website: 993 Elo2026-08-25
Design Arena Website: 993 Elo2026-08-26
Design Arena Website: 986 Elo2026-09-06
Design Arena Website: 992 Elo2026-08-29
Design Arena Website: 992 Elo2026-08-30
Design Arena Website: 992 Elo2026-08-31
Design Arena Website: 992 Elo2026-09-01
Design Arena Website: 991 Elo2026-09-02
Design Arena Website: 989 Elo2026-09-03
Design Arena Website: 988 Elo2026-09-04
LMArena Creative Writing: 1261 Elo2026-07-21
LMArena Creative Writing: 1261 Elo2026-07-27
LMArena Creative Writing: 1261 Elo2026-07-30
LMArena Creative Writing: 1261 Elo2026-08-02
LMArena Creative Writing: 1261 Elo2026-08-03
LMArena Creative Writing: 1261 Elo2026-08-06
LMArena Creative Writing: 1260 Elo2026-08-12
LMArena Creative Writing: 1260 Elo2026-08-21
LMArena Creative Writing: 1260 Elo2026-09-02
LMArena Creative Writing: 1260 Elo2026-08-27
LMArena Creative Writing: 1260 Elo2026-09-01
LMArena Instruction Following: 1267 Elo2026-07-21
LMArena Instruction Following: 1267 Elo2026-07-27
LMArena Instruction Following: 1267 Elo2026-07-30
LMArena Instruction Following: 1267 Elo2026-08-02
LMArena Instruction Following: 1267 Elo2026-08-03
LMArena Instruction Following: 1267 Elo2026-08-06
LMArena Instruction Following: 1267 Elo2026-08-12
LMArena Instruction Following: 1267 Elo2026-08-21
LMArena Instruction Following: 1267 Elo2026-09-02
LMArena Instruction Following: 1267 Elo2026-08-27
LMArena Instruction Following: 1267 Elo2026-09-01
LMArena Long Query: 1283 Elo2026-07-21
LMArena Long Query: 1283 Elo2026-07-27
LMArena Long Query: 1283 Elo2026-07-30
LMArena Long Query: 1283 Elo2026-08-02
LMArena Long Query: 1283 Elo2026-08-03
LMArena Long Query: 1283 Elo2026-08-06
LMArena Long Query: 1282 Elo2026-08-12
LMArena Long Query: 1282 Elo2026-08-21
LMArena Long Query: 1282 Elo2026-09-02
LMArena Long Query: 1283 Elo2026-08-27
LMArena Long Query: 1283 Elo2026-09-01
LMArena Math: 1274 Elo2026-07-21
LMArena Math: 1274 Elo2026-07-27
LMArena Math: 1274 Elo2026-07-30
LMArena Math: 1274 Elo2026-08-02
LMArena Math: 1274 Elo2026-08-03
LMArena Math: 1274 Elo2026-08-06
LMArena Math: 1274 Elo2026-08-12
LMArena Math: 1274 Elo2026-08-21
LMArena Math: 1274 Elo2026-09-01
LMArena Math: 1274 Elo2026-08-27
LMArena Text: 1322 Elo2026-07-21
LMArena Text: 1322 Elo2026-07-27
LMArena Text: 1322 Elo2026-07-30
LMArena Text: 1322 Elo2026-08-02
LMArena Text: 1322 Elo2026-08-10
LMArena Text: 1322 Elo2026-08-06
LMArena Text: 1322 Elo2026-08-03
LMArena Text: 1322 Elo2026-08-21
LMArena Text: 1322 Elo2026-08-12
LMArena Text: 1322 Elo2026-09-01
LMArena Text: 1322 Elo2026-09-02
LMArena Text: 1322 Elo2026-08-27
LMArena Vision: 1089 Elo2026-07-21
LMArena Vision: 1090 Elo2026-07-26
LMArena Vision: 1090 Elo2026-07-30
LMArena Vision: 1089 Elo2026-08-02
LMArena Vision: 1089 Elo2026-08-06
LMArena Vision: 1089 Elo2026-08-21
LMArena Vision: 1089 Elo2026-08-27
SWE-rebench^‡: 0.3% ± 02025-08-01text

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference. ‡ Submitted scaffold plus model result. Compare the harness and effort settings, not only the model name.

Task evidence

How broad is the support?

Each status is exact to this model version and the selected task. Official release claims remain provisional.

Best LLM for Debugging & Code ReviewEstablished evidence
60% of intended weighted task evidence across 2 independent sources. 6 of 6 configured evaluation feeds currently have results.
Best LLM for Business WritingProvisional evidence
70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Marketing CopyProvisional evidence
70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Chat & RoleplayProvisional evidence
70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Roleplay & CharacterProvisional evidence
70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Tool & Function CallingProvisional evidence
65% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or LMArena Search. 4 of 5 configured evaluation feeds currently have results.
Best LLM for Creative WritingProvisional evidence
60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.
Best LLM for WritingProvisional evidence
60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Frontend & UIProvisional evidence
60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 5 of 5 configured evaluation feeds currently have results.
Best Local LLM for CodingProvisional evidence
56% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Hermes AgentProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.
Best LLM for OpenHandsProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.
Best LLM for GooseProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.
Best LLM for OpenClawProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Image UnderstandingProvisional evidence
55% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Reasoning or VLMEvalKit tasks. 3 of 4 configured evaluation feeds currently have results.
Best LLM for a General AssistantProvisional evidence
55% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.
Best LLM for CodingProvisional evidence
50% of intended weighted task evidence across 3 independent sources; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 8 of 8 configured evaluation feeds currently have results.
Best LLM for Logic & Problem SolvingProvisional evidence
50% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.
Best LLM for AI AgentsProvisional evidence
50% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Agentic Coding or LMArena Agent. 7 of 7 configured evaluation feeds currently have results.
Best LLM for Competition MathProvisional evidence
40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Mathematics or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Math & ReasoningProvisional evidence
40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Mathematics or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.
Best Value LLMProvisional evidence
36% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.
Best LLM for JSON & Schema OutputProvisional evidence
33% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Structured-output eval. 4 of 5 configured evaluation feeds currently have results.
Best LLM for Structured Data ExtractionProvisional evidence
33% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Structured-output eval. 4 of 5 configured evaluation feeds currently have results.
Best Open-Weight LLM for Self-HostingProvisional evidence
33% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.
Best LLM for Code CompletionProvisional evidence
31% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 4 of 4 configured evaluation feeds currently have results.
Best LLM for Autonomous AgentsProvisional evidence
29% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Frontier-Bench or LiveBench Agentic Coding. 7 of 7 configured evaluation feeds currently have results.
Best LLM for Fast SummariesProvisional evidence
29% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.
Best LLM for Literary TranslationProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.
Best Cheap LLM for High VolumeProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.
Best LLM for Everyday TranslationProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.
Cheapest Capable LLMProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.
Best LLM for TranslationProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.
Best LLM for Massive ContextProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or LongBench v2. 3 of 4 configured evaluation feeds currently have results.
Best LLM for OCR & DocumentsProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Vision & DocumentsProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Charts & DiagramsProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Document ParsingProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Agentic CodingProvisional evidence
23% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Design Arena Full-stack or Design Arena Web-apps. 8 of 8 configured evaluation feeds currently have results.
Best LLM for Document SummarizationProvisional evidence
20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LiveBench Instruction Following. 4 of 6 configured evaluation feeds currently have results.
Best LLM for SummarizationProvisional evidence
20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LiveBench Instruction Following. 4 of 6 configured evaluation feeds currently have results.
Best LLM for Computer & Browser UseProvisional evidence
20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or OSWorld Verified. 4 of 4 configured evaluation feeds currently have results.
Best LLM for RAG & Long ContextProvisional evidence
18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LMArena Document. 4 of 6 configured evaluation feeds currently have results.
Best LLM for High-Volume ExtractionProvisional evidence
13% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Route reliability. 2 of 4 configured evaluation feeds currently have results.
Best LLM for Grounded RAGProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from CRAG or FACTS Grounding. 2 of 5 configured evaluation feeds currently have results.

Recommendation coverage

Where this model appears

Not currently included in a published recommendation. The task evidence panel above says exactly what is confirmed and what is still missing.

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.