NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/Palmyra X5
writer logo

Palmyra X5

by writer · Released Jan 2026

1M Context
57.0
avg score
Rank #105
Compare
Better than 66% of all models
Context
1.0M tokens (~520 books)
Input $/1M
$0.60
Output $/1M
$6.00
Type
text
License
Proprietary
Benchmarks
5 tested
Data as of
About

Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million...

Tested on 5 benchmarks · BenchGecko score 57.0. Top scores: HELM — IFEval (82.3%), HELM — MMLU-Pro (80.4%), HELM — WildBench (78.0%).

Looking for similar performance at lower cost?
Qwen3 Next 80B A3B Thinking scores 56.8 (100% as good) at $0.15/1M input · 75% cheaper
Capabilities
reasoning
78.0
#22 globally
math
41.5
#149 globally
knowledge
73.3
#13 globally
language
82.3
#51 globally
Benchmark Scores
Compare All
Tested on 5 benchmarks · Ranked across 4 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
reasoningCompare reasoning →
HELM — WildBench

Stanford HELM WildBench evaluation. Tests reasoning on challenging real-world tasks.

78.0·
mathCompare math →
HELM — Omni-MATH

Stanford HELM evaluation of mathematical reasoning across diverse problem types.

41.5·
knowledgeCompare knowledge →
HELM — MMLU-Pro

Stanford HELM evaluation of MMLU-Pro. Tests broad knowledge with increased difficulty.

80.4·
HELM — GPQA

Stanford HELM evaluation of GPQA. Tests graduate-level scientific reasoning.

66.1·
Quick compare:moonshotai logovs Kimi K2.5Alibaba Qwen logovs Qwen3.8 Max (0902)Alibaba Qwen logovs Qwen3 Next 80B A3B Thinking
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Similar Models
moonshotai logo
Kimi K2.5
moonshotai
57.1$0.45/1M
Alibaba Qwen logo
Qwen3.8 Max (0902)
Alibaba Qwen
56.8$2.00/1M
Alibaba Qwen logo
Qwen3 Next 80B A3B Thinking
Alibaba Qwen
56.8$0.15/1M
Links
Info
writerPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@writer
BenchGecko API
palmyra-x5
Specifications
  • Typetext
  • Context1.0M tokens (~520 books)
  • ReleasedJan 2026
  • LicenseProprietary
  • StatusActive
  • Cost / Message~$0.007
Available On
writer logowriter$0.60
Categories
reasoningmathknowledgelanguage
Learn More
context-windowtransformertokens
Share & Export
Tweet
Related Models
moonshotai logoKimi K2.5
57.1
Alibaba Qwen logoQwen3.8 Max (0902)
56.8
Alibaba Qwen logoQwen3 Next 80B A3B Thinking
56.8
DeepSeek logoDeepSeek-Coder-V2-Lite-Base
57.4
Palmyra X5 is a proprietary text AI model by writer, released in January 2026. It has an average benchmark score of 57.0. Context window: 1M tokens.

Related Models

Kimi K2.5 · moonshotaiQwen3.8 Max (0902) · Alibaba QwenQwen3 Next 80B A3B Thinking · Alibaba QwenDeepSeek-Coder-V2-Lite-Base · DeepSeekGrok 4.20 · xAI

Benchmarks

HELM — IFEvalHELM — MMLU-ProHELM — WildBenchHELM — GPQAHELM — Omni-MATH

Related Pages

writer · Providerwriter · EconomyAll ModelsCompare ModelsPricingDevelopers · APIContext Window · Glossary

Key facts · as of 2026-10-05

  • Palmyra X5 by writer. BenchGecko score 57.0, rank 105 of 312 scored models (normalized average of public benchmark scores).
  • List price $0.60 input · $6.00 output per 1M tokens (as of 2026-10-05).
  • Sold by 1 provider (as of 2026-10-05): Amazon Bedrock $0.60 in / $6.00 out.

How to cite · data as of 2026-10-05

Palmyra X5 · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/palmyra-x5

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP