# Coding Agent Index v2.0: Claude Opus 5.5 Leads at 61.7

> Artificial Analysis rebuilt its Coding Agent Index around FrontierCode. Claude Code with Opus 5.5 leads at 61.7. The scores, costs and what changed.

- Author: Nitish Garg, Founder & CEO, CellCog
- Published: 2026-10-23
- Canonical (HTML): https://cellcog.ai/blog/artificial-analysis-coding-agent-index/
- Section: Guides / Choosing a platform
- Publisher: CellCog (https://cellcog.ai), the AI employee platform. Blog index for agents: https://cellcog.ai/blog/llms.txt

## Key points

- Artificial Analysis launched Coding Agent Index v2.0 on October 23, 2026. It scores a model together with its agent harness across 290 tasks.
- Claude Code with Claude Opus 5.5 leads at 61.7, ahead of Claude Code with Sonnet 5.5 at 59.3 and Muse Code with Muse Wonder Full at 58.9.
- Cognition's FrontierCode replaces DeepSWE. It grades whether a maintainer would merge the change, and Opus 5.5 leads it at 56.0%.
- Stricter grading on repository Q&A dropped the average of 21 returning configurations from 58.8% to 57.1%.
- The top score costs the most: $11.42 per task for Opus 5.5 in Claude Code against $0.39 for DeepSeek V4.1 Flash in Codex at 47.3.

## At a glance

- **Who leads Coding Agent Index v2.0?** Claude Code running Claude Opus 5.5 at max effort, with 61.7. The next three configurations score 59.3, 58.9 and 57.6.
- **What changed from v1.5?** Cognition's FrontierCode replaced DeepSWE, and the repository Q&A benchmark got revised rubrics and a new judge.
- **What does the top score cost?** $11.42 per task in pay-per-token API cost, about 29 times the $0.39 of the cheapest configuration on the cost frontier.

**Artificial Analysis launched version 2.0 of its Coding Agent Index on October 23, 2026, and Claude Code running Claude Opus 5.5 leads it at 61.7.** The index scores a model and its agent harness together, so the leaderboard ranks combinations like Claude Code with Opus 5.5 or Codex with GPT-6.1 Sol rather than bare models.

Version 2.0 swaps in Cognition's FrontierCode for DeepSWE and tightens the grading of repository Q&A. This page reads the [announcement on X](https://x.com/ArtificialAnlys/status/2113424551396934134), posted at 00:17 UTC, and the index on [artificialanalysis.ai](https://artificialanalysis.ai/). Every number below is theirs.

## The top four

The index now covers 290 tasks across software engineering, terminal use and repository Q&A, "with the three benchmarks weighted equally." The top four sit within 4.1 points of each other, and three of them run in Claude Code.

*Table: Coding Agent Index v2.0, top four configurations (Artificial Analysis, Oct 23 2026)*

| Rank | Harness and model (setting) | Index score |
|---|---|---|
| 1 | Claude Code, Claude Opus 5.5 (max) | 61.7 |
| 2 | Claude Code, Claude Sonnet 5.5 (max) | 59.3 |
| 3 | Muse Code, Muse Wonder Full (max) | 58.9 |
| 4 | Claude Code, Claude Fable 5.1 (max with fallback) | 57.6 |

Meta's Muse Code is the only harness outside Anthropic in the top four. The first OpenAI entry, Codex with GPT-6 Astra, scores 54.7.

## What FrontierCode changes

FrontierCode v1.1 replaces DeepSWE v1.1. It is Cognition's benchmark: 100 software engineering tasks on real open-source repositories, with a private test set, "graded on whether a maintainer would merge the change."

- **Blocking checks decide pass or fail.** An attempt that fails one scores zero.
- **Non-blocking checks decide how good.** An attempt that passes every blocking check scores between 70% and 100%.
- **Shortcuts score zero.** Artificial Analysis scans each run with a modified version of Cognition's rule-based scanner, and "any attempt flagged for accessing solution material scores zero."

![Animation: three code changes reach a gate of blocking checks; one fails and scores 0, one passes and lands in the 70 to 100 band, one is flagged for solution material and scores 0](https://cellcog.ai/blog/media/artificial-analysis-coding-agent-index/frontiercode-grading.svg)
*How FrontierCode grades an attempt: a failed blocking check or a shortcut scores zero*

This is where Opus 5.5 pulls ahead. On FrontierCode alone it scores 56.0%, against 52.6% for Codex with DeepSeek V4.1 Flash, 49.4% for Codex with GPT-6.1 Sol and 49.3% for Codex with GPT-6 Astra. Below the top the field is crowded: 15 of the 24 configurations score between 43% and 49%.

## Stricter repository Q&A

The third benchmark keeps Scale AI's 124 repository Q&A tasks and changes how they are judged. Artificial Analysis reworded 127 of the 1,306 rubric criteria, moved the judge to GPT-6 Luna at xhigh, and takes five votes per criterion. It renamed the result SWE-Atlas-QnA-AA and published the dataset and judge setup on Hugging Face.

The effect is a lower bar for everyone. Across the 21 configurations scored on both versions, the average fell 1.7 points, from 58.8% to 57.1%, and 14 of 21 moved down. Muse Code with Muse Spark Open fell 7.0 points; Codex with GPT-6.1 Sol gained 2.1.

## The cost frontier

Four configurations sit on the cost frontier, where no other configuration scores higher for less money.

*Table: Coding Agent Index v2.0 cost frontier, API cost per task*

| Configuration | Index score | Cost per task |
|---|---|---|
| Codex, DeepSeek V4.1 Flash (max) | 47.3 | $0.39 |
| Codex, GPT-6.1 Sol (max) | 54.1 | $1.50 |
| Codex, GPT-6 Astra (max) | 54.7 | $7.04 |
| Claude Code, Claude Opus 5.5 (max) | 61.7 | $11.42 |

![Animation: four dots on score versus API cost per task, DeepSeek V4.1 Flash 47.3 at $0.39, GPT-6.1 Sol 54.1 at $1.50, GPT-6 Astra 54.7 at $7.04, and Opus 5.5 61.7 at $11.42 highlighted](https://cellcog.ai/blog/media/artificial-analysis-coding-agent-index/cost-frontier.svg)
*The four configurations on the cost frontier; the top score costs the most per task*

The spread is wide. The top score costs about 29 times the cheapest frontier point for 14.4 more points. GPT-6.1 Sol in Codex gets 54.1 for $1.50, a fraction of the price of Astra for almost the same score. Artificial Analysis adds: "Costs are pay-per-token API costs, not subscription prices."

## What the index does and does not tell you

- **It ranks pairs, not models.** Opus 5.5 is measured inside Claude Code; the same model in another harness can score differently.
- **Max effort everywhere.** Every leading entry runs at max or xhigh, which is also what drives the cost column.
- **Benchmarks still disagree.** The same day, a [widely shared run of SlopCodeBench](https://x.com/NotRyanB/status/2113357440959791299), which makes agents extend one program across several specs, put GPT-6 Astra and Sol at the top with scores near 16%. Long, changing work remains far from solved.

For us the result lands close to home: CellCog's AI employees run on Claude Opus 5.5. The index tests Claude Code, not our harness, so we read it as a statement about the model, not about us.

## What to watch

- Artificial Analysis says it will keep updating the index "with more evaluations and agents to come."
- Whether Cursor, Grok Build and Kimi Code get scored on v2.0.
- Whether the next model releases move the FrontierCode ceiling above 56.0%.

## FAQ

**What is the Artificial Analysis Coding Agent Index?**

An index that scores coding agents as a model plus its harness, such as Claude Code with Opus 5.5 or Codex with GPT-6.1 Sol. Version 2.0 averages three benchmarks with equal weight across 290 tasks.

**Which benchmarks are in v2.0?**

FrontierCode v1.1 from Cognition for software engineering, Terminal-Bench 4.0 for terminal work, and SWE-Atlas-QnA-AA, Scale AI's repository Q&A tasks with rubrics revised by Artificial Analysis.

**How does FrontierCode score an attempt?**

It asks whether a maintainer would merge the change. Failing a blocking check scores zero; passing all of them scores 70% to 100% depending on the non-blocking checks, and an attempt flagged for using solution material scores zero.

**Is Opus 5.5 the best value?**

It has the top score, not the lowest cost. Four configurations sit on the cost frontier, from DeepSeek V4.1 Flash in Codex at $0.39 a task to Opus 5.5 in Claude Code at $11.42.

**Do the costs match a Claude or ChatGPT subscription?**

No. Artificial Analysis states the costs are pay-per-token API costs, not subscription prices.

## Related

- [Claude Opus 5.5 Is Out: Price, Specs, Every Leak Graded](https://cellcog.ai/blog/claude-opus-5-5-release-date/index.md)
- [What Is Muse Code? Meta's Terminal Coding Agent, Explained](https://cellcog.ai/blog/what-is-muse-code/index.md)
- [Best AI Agent Harnesses: October 2026 Rankings](https://cellcog.ai/blog/best-ai-agent-harnesses/index.md)

## The AI employee for this read

[AI Software Engineer](https://cellcog.ai/ai-employees/ai-software-engineer): I built this page. For what it covers, hire an engineer: it works in your repo behind an approval gate, so nothing reaches your world unclassified.

---

Markdown alternate of https://cellcog.ai/blog/artificial-analysis-coding-agent-index/. Try CellCog free, no credit card needed: https://cellcog.ai/signup