Skip to content

Model comparison

How close are DeepSeek and Qwen to Claude?

In regions where Claude, GPT and Gemini are unavailable, SOVEREIGN offers models such as DeepSeek and Qwen. Below are our own measurements on 40 automatically graded tasks and public benchmarks — including where Claude is still stronger.

Measured on 2026-09-27

Open SOVEREIGN →

Measured result

  • Qwen 3.8 27B scored 92.5% of Claude Opus 4.8's result on our tasks (37 vs 40 solved) at about 5× lower cost. This is not parity: Claude Opus 4.8 solved more tasks. See the table below for where the gap is.
  • In our run Claude Opus 4.8 was ahead in: Coding, Instruction following.
  • Not measured yet: Claude Opus 5, Claude Sonnet 5, DeepSeek V4 Pro, DeepSeek V4.1 Flash, Qwen 3.8 Max. Their API route was unavailable during this run (no credits/quota). We don't publish estimates in place of measurements.

Our eval: 40 tasks, graded automatically

Every task is checked by code, not by a person or another AI: unit tests for programs, exact answers for math, strict rules for instructions and text. Mostly in Russian, a few in Uzbek and English.

Eval results table
ModelCoding15 tasksMath & logic10 tasksInstruction following8 tasksRussian text & translation7 tasksOverallMedian latencyCost of 40 tasksRoute
Claude Opus 4.8reference100%(15/15)100%(10/10)100%(8/8)100%(7/7)100%(40/40)3.6 s$0.16rsi
Qwen 3.8 27B93.3%(14/15)100%(10/10)75%(6/8)100%(7/7)92.5%(37/40)0.5 s$0.030groq
Claude Opus 5not measured yet
Claude Sonnet 5not measured yet
DeepSeek V4 Pronot measured yet
DeepSeek V4.1 Flashnot measured yet
Qwen 3.8 Maxnot measured yet

Cost = tokens used × the OpenRouter list price for the same model. Latency depends on the provider's hardware (Groq is unusually fast), not only on the model.

Per-task results
TaskClaude Opus 4.8Qwen 3.8 27B
js-plural-ru · rupasspass
js-palindrome-ru · rupasspass
js-merge-intervals · rupasspass
js-roman · rupasspass
js-parse-duration · rupasspass
js-flatten · rupasspass
js-format-rub · rupasspass
js-eval-rpn · enpasspass
py-top-k-words · rupasspass
py-inn · rupassfail
py-spiral · rupasspass
py-lcs · rupasspass
py-to-snake · uzpasspass
py-dijkstra · rupasspass
py-wrap-text · rupasspass
math-trains · rupasspass
math-divisors · rupasspass
math-dice · rupasspass
math-distinct-digits · rupasspass
math-sisters · rupasspass
math-modpow · rupasspass
math-walls-uz · uzpasspass
math-sequence · rupasspass
math-weekday · rupasspass
math-factorial-en · enpasspass
if-json-object · rupasspass
if-json-sorted · rupasspass
if-three-sentences · rupasspass
if-keywords · rupassfail
if-no-letter-o · rupassfail
if-numbered-list · rupasspass
if-answer-in-russian · enpasspass
if-uppercase · rupasspass
wr-en-ru · rupasspass
wr-ru-en · rupasspass
wr-uz-ru · rupasspass
wr-ru-uz · uzpasspass
wr-business-email · rupasspass
wr-summary · rupasspass
wr-product · rupasspass

Public benchmarks

Figures copied from the linked pages on 2026-09-27. In places the model versions differ from the ones we measured — check the exact model name in each row.

Artificial Analysis Intelligence Index v4.3.2

independent

Composite intelligence index (10 evaluations), points.

ModelScore
Claude Opus 5.5 (max with fallback)58
Qwen3.8 Max (0902)45
DeepSeek V4.1 Flash (max)39
Claude Sonnet 5 (max)38
DeepSeek V4 Pro 0813 (max)36
Qwen3.8 27B (xhigh)34

Source: artificialanalysis.ai/leaderboards/models · 2026-09-27

LMArena — Text

independent

Rating from blind human votes (Elo), text.

ModelScore
claude-opus-5-high1491 ± 4
claude-opus-4-8-high1480 ± 4
qwen3.8-max1479 ± 5
deepseek-v4.1-flash-max1477 ± 8
deepseek-v4-pro-high-202608131464 ± 7
claude-sonnet-5-high1462 ± 4
qwen3.8-27b1438 ± 6

Source: arena.ai/leaderboard/text · 2026-09-25

Humanity's Last Exam (Artificial Analysis)

independent

Hardest expert questions, % correct.

ModelScore
Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)61%
Qwen3.8 Max (0902)43%
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)41%
DeepSeek V4 Pro 0813 (Reasoning, Max Effort)41%

Source: artificialanalysis.ai/models/comparisons/claude-opus-5-5-vs-deepseek-v4-pro, artificialanalysis.ai/models/comparisons/claude-sonnet-5-vs-qwen3-8-max · 2026-09-27

Terminal-Bench 4.0 (Artificial Analysis)

independent

Agentic coding in a terminal, % solved.

ModelScore
Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)60%
Qwen3.8 Max (0902)39%
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)14%
DeepSeek V4 Pro 0813 (Reasoning, Max Effort)14%

Source: artificialanalysis.ai/models/comparisons/claude-opus-5-5-vs-deepseek-v4-pro, artificialanalysis.ai/models/comparisons/claude-sonnet-5-vs-qwen3-8-max · 2026-09-27

SWE-bench Verified

self-reported by vendors

Fixing real GitHub issues, % resolved.

ModelScore
Claude Opus 4.888.6%
Claude Sonnet 585.2%
DeepSeek-V4-Pro-Max80.6%
Qwen3.7 Max80.4%
DeepSeek-V4-Flash-Max79.0%

Source: llm-stats.com/benchmarks/swe-bench-verified · 2026-09-27

Methodology and limitations

  • 40 tasks, 1 run per model, on 2026-09-27. Temperature 0 where supported.
  • Models are called through the same provider routes the app itself uses (OpenRouter, RSI, Groq, OmniRoute); the route actually used is shown in the table.
  • Code is checked with hidden unit tests in an isolated process (no network, with a timeout) — all tests must pass.
  • Text tasks check only alphabet, length and required terms — style and fluency are not judged.
  • This is a small, focused test, not a full benchmark: a single run can vary, and 40 tasks cannot cover everything.
  • Per public benchmarks, Claude's top models are still ahead at agentic coding in a terminal (Terminal-Bench) and on the hardest expert questions (Humanity's Last Exam).
  • Cost and latency are indicative: real prices differ on resellers and free tiers.

FAQ

Do DeepSeek or Qwen work exactly like Claude?

No, and we don't claim that. On many everyday tasks they are close — see the measured numbers above — but not identical, and Claude is ahead on some tasks.

Why can't I choose Claude in my region?

Some model providers don't serve certain regions. We only offer models whose providers allow your region.

Which model should I use for code?

Check the Coding column and pick the best-scoring model available to you. For long agentic work, public benchmarks show a larger gap to Claude.

How often is this page updated?

When models are added or updated, we rerun the eval and update the date above.