DeepSeek V4.1 Flash vs Qwen3.8 Flash
Same documents, same prompt: where each model gets it right, what it really costs, and how fast it responds.
Verdict
DeepSeek V4.1 Flash is more accurate and cheaper in 28 of 30 combinations.
More accurate
DeepSeek V4.1 Flash
wins 23 of 30
Cheaper
DeepSeek V4.1 Flash
cheaper in 28 of 30
Faster
DeepSeek V4.1 Flash
5.0 sec vs 14.1 sec
Fewer fixes
DeepSeek V4.1 Flash
13 vs 67 documents per 1,000
Across 30 task and document-language combinations (speed and fixes: median).
At a glance
| Accuracy (correct fields) | Per 1,000 documents | |||||
|---|---|---|---|---|---|---|
| Task · documents | DeepSeek V4.1 Flash | Qwen3.8 Flash | Difference | DeepSeek V4.1 Flash | Qwen3.8 Flash | Difference |
| Invoice extraction | 99.39% | 82.36% | ▼ 17.03 | $0.52 | $1.15 | +122 % |
| Email triage | 97.63% | 97.48% | ▼ 0.15 | $0.23 | $0.30 | +31 % |
| Personal data detection | 99.62% | 99.24% | ▼ 0.38 | $0.29 | $0.28 | −2 % |
| Contract clauses | 100.00% | 95.13% | ▼ 4.87 | $0.32 | $0.62 | +93 % |
| Document summaries | 100.00% | 99.89% | ▼ 0.11 | $0.54 | $0.75 | +37 % |
| Questions about a document | 99.22% | 99.78% | ▲ 0.56 | $0.31 | $0.44 | +41 % |
| Accuracy (correct fields) | Per 1,000 documents | |||||
|---|---|---|---|---|---|---|
| Task · documents | DeepSeek V4.1 Flash | Qwen3.8 Flash | Difference | DeepSeek V4.1 Flash | Qwen3.8 Flash | Difference |
| Invoice extraction | 99.90% | 91.79% | ▼ 8.11 | $0.50 | $1.02 | +105 % |
| Email triage | 97.41% | 98.52% | ▲ 1.11 | $0.30 | $0.45 | +51 % |
| Personal data detection | 99.71% | 96.95% | ▼ 2.76 | $0.31 | $0.41 | +29 % |
| Contract clauses | 100.00% | 99.90% | ▼ 0.1 | $0.42 | $0.63 | +50 % |
| Document summaries | 100.00% | 95.44% | ▼ 4.56 | $0.78 | $1.48 | +90 % |
| Questions about a document | 100.00% | 94.22% | ▼ 5.78 | $0.38 | $0.71 | +87 % |
| Accuracy (correct fields) | Per 1,000 documents | |||||
|---|---|---|---|---|---|---|
| Task · documents | DeepSeek V4.1 Flash | Qwen3.8 Flash | Difference | DeepSeek V4.1 Flash | Qwen3.8 Flash | Difference |
| Invoice extraction | 99.54% | 93.49% | ▼ 6.05 | $0.57 | $1.12 | +98 % |
| Email triage | 96.37% | 97.85% | ▲ 1.48 | $0.30 | $0.39 | +29 % |
| Personal data detection | 99.81% | 99.62% | ▼ 0.19 | $0.31 | $0.36 | +17 % |
| Contract clauses | 97.08% | 98.00% | ▲ 0.92 | $0.52 | $0.78 | +51 % |
| Document summaries | 100.00% | 95.33% | ▼ 4.67 | $0.62 | $1.43 | +132 % |
| Questions about a document | 100.00% | 98.89% | ▼ 1.11 | $0.33 | $0.46 | +41 % |
| Accuracy (correct fields) | Per 1,000 documents | |||||
|---|---|---|---|---|---|---|
| Task · documents | DeepSeek V4.1 Flash | Qwen3.8 Flash | Difference | DeepSeek V4.1 Flash | Qwen3.8 Flash | Difference |
| Invoice extraction | 98.21% | 88.87% | ▼ 9.34 | $0.65 | $1.38 | +113 % |
| Email triage | 96.52% | 96.74% | ▲ 0.22 | $0.34 | $0.46 | +34 % |
| Personal data detection | 99.90% | 99.81% | ▼ 0.09 | $0.44 | $0.38 | −13 % |
| Contract clauses | 100.00% | 100.00% | ±0 | $0.40 | $0.60 | +49 % |
| Document summaries | 100.00% | 94.44% | ▼ 5.56 | $0.88 | $1.22 | +40 % |
| Questions about a document | 100.00% | 99.67% | ▼ 0.33 | $0.35 | $0.53 | +51 % |
| Accuracy (correct fields) | Per 1,000 documents | |||||
|---|---|---|---|---|---|---|
| Task · documents | DeepSeek V4.1 Flash | Qwen3.8 Flash | Difference | DeepSeek V4.1 Flash | Qwen3.8 Flash | Difference |
| Invoice extraction | 99.54% | 90.46% | ▼ 9.08 | $0.60 | $1.28 | +114 % |
| Email triage | 96.74% | 96.44% | ▼ 0.3 | $0.34 | $0.45 | +35 % |
| Personal data detection | 99.71% | 99.71% | ±0 | $0.37 | $0.40 | +6 % |
| Contract clauses | 99.85% | 99.49% | ▼ 0.36 | $0.45 | $0.66 | +47 % |
| Document summaries | 100.00% | 96.33% | ▼ 3.67 | $0.78 | $1.46 | +87 % |
| Questions about a document | 100.00% | 98.78% | ▼ 1.22 | $0.36 | $0.57 | +58 % |
Difference: Qwen3.8 Flash vs. DeepSeek V4.1 Flash; accuracy in percentage points, price in percent. The better value is in bold. Click a task to see the details.
Invoice extraction · English (US) (150 documents)
DeepSeek V4.1 Flash is more accurate by 17 pp. DeepSeek V4.1 Flash is 2.2× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 99.39% | 82.36% |
| Error-free documents | 93.33% | 57.33% |
| Per 1,000 documents | $0.52 | $1.15 |
| To fix / 1,000 | 67 | 427 |
| Speed (median) | 5.7 sec | 17.4 sec |
| Valid answers | 100.00% | 90.67% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Invoice extraction · Czech (150 documents)
DeepSeek V4.1 Flash is more accurate by 8.1 pp. DeepSeek V4.1 Flash is 2.1× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 99.90% | 91.79% |
| Error-free documents | 98.67% | 76.67% |
| Per 1,000 documents | $0.50 | $1.02 |
| To fix / 1,000 | 13 | 233 |
| Speed (median) | 5.0 sec | 17.0 sec |
| Valid answers | 100.00% | 96.67% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Invoice extraction · German (150 documents)
DeepSeek V4.1 Flash is more accurate by 6.1 pp. DeepSeek V4.1 Flash is 2× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 99.54% | 93.49% |
| Error-free documents | 94.00% | 87.33% |
| Per 1,000 documents | $0.57 | $1.12 |
| To fix / 1,000 | 60 | 127 |
| Speed (median) | 6.4 sec | 19.0 sec |
| Valid answers | 100.00% | 94.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Invoice extraction · Spanish (150 documents)
DeepSeek V4.1 Flash is more accurate by 9.3 pp. DeepSeek V4.1 Flash is 2.1× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 98.21% | 88.87% |
| Error-free documents | 77.33% | 74.67% |
| Per 1,000 documents | $0.65 | $1.38 |
| To fix / 1,000 | 227 | 253 |
| Speed (median) | 6.3 sec | 22.0 sec |
| Valid answers | 100.00% | 90.67% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Invoice extraction · French (150 documents)
DeepSeek V4.1 Flash is more accurate by 9.1 pp. DeepSeek V4.1 Flash is 2.1× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 99.54% | 90.46% |
| Error-free documents | 94.00% | 83.33% |
| Per 1,000 documents | $0.60 | $1.28 |
| To fix / 1,000 | 60 | 167 |
| Speed (median) | 6.2 sec | 19.4 sec |
| Valid answers | 100.00% | 94.67% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Email triage · English (US) (150 documents)
DeepSeek V4.1 Flash is more accurate by 0.1 pp. DeepSeek V4.1 Flash is 1.3× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 97.63% | 97.48% |
| Error-free documents | 78.67% | 78.67% |
| Per 1,000 documents | $0.23 | $0.30 |
| To fix / 1,000 | 213 | 213 |
| Speed (median) | 3.8 sec | 8.9 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Email triage · Czech (150 documents)
Qwen3.8 Flash is more accurate by 1.1 pp. DeepSeek V4.1 Flash is 1.5× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 97.41% | 98.52% |
| Error-free documents | 77.33% | 86.67% |
| Per 1,000 documents | $0.30 | $0.45 |
| To fix / 1,000 | 227 | 133 |
| Speed (median) | 4.2 sec | 13.0 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Email triage · German (150 documents)
Qwen3.8 Flash is more accurate by 1.5 pp. DeepSeek V4.1 Flash is 1.3× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 96.37% | 97.85% |
| Error-free documents | 68.00% | 81.33% |
| Per 1,000 documents | $0.30 | $0.39 |
| To fix / 1,000 | 320 | 187 |
| Speed (median) | 4.2 sec | 12.1 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Email triage · Spanish (150 documents)
Qwen3.8 Flash is more accurate by 0.2 pp. DeepSeek V4.1 Flash is 1.3× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 96.52% | 96.74% |
| Error-free documents | 72.00% | 72.00% |
| Per 1,000 documents | $0.34 | $0.46 |
| To fix / 1,000 | 280 | 280 |
| Speed (median) | 5.5 sec | 11.2 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Email triage · French (150 documents)
DeepSeek V4.1 Flash is more accurate by 0.3 pp. DeepSeek V4.1 Flash is 1.3× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 96.74% | 96.44% |
| Error-free documents | 72.67% | 76.00% |
| Per 1,000 documents | $0.34 | $0.45 |
| To fix / 1,000 | 273 | 240 |
| Speed (median) | 5.2 sec | 13.2 sec |
| Valid answers | 100.00% | 99.33% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Personal data detection · English (US) (150 documents)
DeepSeek V4.1 Flash is more accurate by 0.4 pp.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 99.62% | 99.24% |
| Error-free documents | 97.33% | 98.67% |
| Per 1,000 documents | $0.29 | $0.28 |
| To fix / 1,000 | 27 | 13 |
| Speed (median) | 3.8 sec | 7.5 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Personal data detection · Czech (150 documents)
DeepSeek V4.1 Flash is more accurate by 2.8 pp. DeepSeek V4.1 Flash is 1.3× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 99.71% | 96.95% |
| Error-free documents | 98.00% | 88.67% |
| Per 1,000 documents | $0.31 | $0.41 |
| To fix / 1,000 | 20 | 113 |
| Speed (median) | 4.2 sec | 9.6 sec |
| Valid answers | 100.00% | 99.33% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Personal data detection · German (150 documents)
DeepSeek V4.1 Flash is more accurate by 0.2 pp. DeepSeek V4.1 Flash is 1.2× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 99.81% | 99.62% |
| Error-free documents | 98.67% | 99.33% |
| Per 1,000 documents | $0.31 | $0.36 |
| To fix / 1,000 | 13 | 7 |
| Speed (median) | 3.7 sec | 12.2 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Personal data detection · Spanish (150 documents)
DeepSeek V4.1 Flash is more accurate by 0.1 pp. Qwen3.8 Flash is 1.2× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 99.90% | 99.81% |
| Error-free documents | 99.33% | 98.67% |
| Per 1,000 documents | $0.44 | $0.38 |
| To fix / 1,000 | 7 | 13 |
| Speed (median) | 5.9 sec | 10.2 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Personal data detection · French (150 documents)
Both are equally accurate. DeepSeek V4.1 Flash is 1.1× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 99.71% | 99.71% |
| Error-free documents | 98.00% | 98.00% |
| Per 1,000 documents | $0.37 | $0.40 |
| To fix / 1,000 | 20 | 20 |
| Speed (median) | 5.3 sec | 10.9 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Contract clauses · English (US) (150 documents)
DeepSeek V4.1 Flash is more accurate by 4.9 pp. DeepSeek V4.1 Flash is 1.9× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 100.00% | 95.13% |
| Error-free documents | 100.00% | 69.33% |
| Per 1,000 documents | $0.32 | $0.62 |
| To fix / 1,000 | 0 | 307 |
| Speed (median) | 3.9 sec | 14.1 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Contract clauses · Czech (150 documents)
DeepSeek V4.1 Flash is more accurate by 0.1 pp. DeepSeek V4.1 Flash is 1.5× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 100.00% | 99.90% |
| Error-free documents | 100.00% | 98.67% |
| Per 1,000 documents | $0.42 | $0.63 |
| To fix / 1,000 | 0 | 13 |
| Speed (median) | 4.3 sec | 13.6 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Contract clauses · German (150 documents)
Qwen3.8 Flash is more accurate by 0.9 pp. DeepSeek V4.1 Flash is 1.5× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 97.08% | 98.00% |
| Error-free documents | 76.00% | 87.33% |
| Per 1,000 documents | $0.52 | $0.78 |
| To fix / 1,000 | 240 | 127 |
| Speed (median) | 4.7 sec | 19.7 sec |
| Valid answers | 100.00% | 99.33% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Contract clauses · Spanish (150 documents)
Both are equally accurate. DeepSeek V4.1 Flash is 1.5× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 100.00% | 100.00% |
| Error-free documents | 100.00% | 100.00% |
| Per 1,000 documents | $0.40 | $0.60 |
| To fix / 1,000 | 0 | 0 |
| Speed (median) | 4.1 sec | 14.2 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Contract clauses · French (150 documents)
DeepSeek V4.1 Flash is more accurate by 0.4 pp. DeepSeek V4.1 Flash is 1.5× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 99.85% | 99.49% |
| Error-free documents | 98.00% | 93.33% |
| Per 1,000 documents | $0.45 | $0.66 |
| To fix / 1,000 | 20 | 67 |
| Speed (median) | 5.2 sec | 16.2 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Document summaries · English (US) (150 documents)
DeepSeek V4.1 Flash is more accurate by 0.1 pp. DeepSeek V4.1 Flash is 1.4× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 100.00% | 99.89% |
| Error-free documents | 100.00% | 99.33% |
| Per 1,000 documents | $0.54 | $0.75 |
| To fix / 1,000 | 0 | 7 |
| Speed (median) | 8.8 sec | 17.8 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Document summaries · Czech (150 documents)
DeepSeek V4.1 Flash is more accurate by 4.6 pp. DeepSeek V4.1 Flash is 1.9× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 100.00% | 95.44% |
| Error-free documents | 100.00% | 93.33% |
| Per 1,000 documents | $0.78 | $1.48 |
| To fix / 1,000 | 0 | 67 |
| Speed (median) | 13.4 sec | 34.2 sec |
| Valid answers | 100.00% | 96.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Document summaries · German (150 documents)
DeepSeek V4.1 Flash is more accurate by 4.7 pp. DeepSeek V4.1 Flash is 2.3× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 100.00% | 95.33% |
| Error-free documents | 100.00% | 95.33% |
| Per 1,000 documents | $0.62 | $1.43 |
| To fix / 1,000 | 0 | 47 |
| Speed (median) | 9.8 sec | 29.5 sec |
| Valid answers | 100.00% | 95.33% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Document summaries · Spanish (150 documents)
DeepSeek V4.1 Flash is more accurate by 5.6 pp. DeepSeek V4.1 Flash is 1.4× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 100.00% | 94.44% |
| Error-free documents | 100.00% | 93.33% |
| Per 1,000 documents | $0.88 | $1.22 |
| To fix / 1,000 | 0 | 67 |
| Speed (median) | 10.6 sec | 23.9 sec |
| Valid answers | 100.00% | 94.67% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Document summaries · French (150 documents)
DeepSeek V4.1 Flash is more accurate by 3.7 pp. DeepSeek V4.1 Flash is 1.9× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 100.00% | 96.33% |
| Error-free documents | 100.00% | 94.67% |
| Per 1,000 documents | $0.78 | $1.46 |
| To fix / 1,000 | 0 | 53 |
| Speed (median) | 10.5 sec | 28.1 sec |
| Valid answers | 100.00% | 96.67% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Questions about a document · English (US) (150 documents)
Qwen3.8 Flash is more accurate by 0.6 pp. DeepSeek V4.1 Flash is 1.4× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 99.22% | 99.78% |
| Error-free documents | 98.67% | 98.67% |
| Per 1,000 documents | $0.31 | $0.44 |
| To fix / 1,000 | 13 | 13 |
| Speed (median) | 4.2 sec | 8.7 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Questions about a document · Czech (150 documents)
DeepSeek V4.1 Flash is more accurate by 5.8 pp. DeepSeek V4.1 Flash is 1.9× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 100.00% | 94.22% |
| Error-free documents | 100.00% | 84.67% |
| Per 1,000 documents | $0.38 | $0.71 |
| To fix / 1,000 | 0 | 153 |
| Speed (median) | 3.5 sec | 14.3 sec |
| Valid answers | 100.00% | 98.67% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Questions about a document · German (150 documents)
DeepSeek V4.1 Flash is more accurate by 1.1 pp. DeepSeek V4.1 Flash is 1.4× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 100.00% | 98.89% |
| Error-free documents | 100.00% | 96.67% |
| Per 1,000 documents | $0.33 | $0.46 |
| To fix / 1,000 | 0 | 33 |
| Speed (median) | 3.0 sec | 8.6 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Questions about a document · Spanish (150 documents)
DeepSeek V4.1 Flash is more accurate by 0.3 pp. DeepSeek V4.1 Flash is 1.5× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 100.00% | 99.67% |
| Error-free documents | 100.00% | 98.67% |
| Per 1,000 documents | $0.35 | $0.53 |
| To fix / 1,000 | 0 | 13 |
| Speed (median) | 3.3 sec | 10.3 sec |
| Valid answers | 100.00% | 100.00% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.
Questions about a document · French (150 documents)
DeepSeek V4.1 Flash is more accurate by 1.2 pp. DeepSeek V4.1 Flash is 1.6× cheaper.
| Metric | DeepSeek V4.1 Flash | Qwen3.8 Flash |
|---|---|---|
| Correct fields | 100.00% | 98.78% |
| Error-free documents | 100.00% | 97.33% |
| Per 1,000 documents | $0.36 | $0.57 |
| To fix / 1,000 | 0 | 27 |
| Speed (median) | 3.6 sec | 10.4 sec |
| Valid answers | 100.00% | 99.33% |
Free with login
Accuracy field by field and the documents where the models differ.
Just your email, no password.